diff --git a/STAT6101/2a3a.jpg b/STAT6101/2a3a.jpg new file mode 100644 index 0000000..e464fb7 Binary files /dev/null and b/STAT6101/2a3a.jpg differ diff --git a/STAT6101/2a3b.jpg b/STAT6101/2a3b.jpg new file mode 100644 index 0000000..9f1e088 Binary files /dev/null and b/STAT6101/2a3b.jpg differ diff --git a/STAT6101/3a_rha.pdf b/STAT6101/3a_rha.pdf new file mode 100644 index 0000000..5341da8 Binary files /dev/null and b/STAT6101/3a_rha.pdf differ diff --git a/STAT6101/4a2a.png b/STAT6101/4a2a.png new file mode 100644 index 0000000..24535d5 Binary files /dev/null and b/STAT6101/4a2a.png differ diff --git a/STAT6101/4a2b.png b/STAT6101/4a2b.png new file mode 100644 index 0000000..f3637aa Binary files /dev/null and b/STAT6101/4a2b.png differ diff --git a/STAT6101/6a3b.pdf b/STAT6101/6a3b.pdf new file mode 100644 index 0000000..ca94f80 Binary files /dev/null and b/STAT6101/6a3b.pdf differ diff --git a/STAT6101/Assignment_1b.Rmd b/STAT6101/Assignment_1b.Rmd new file mode 100644 index 0000000..1c594f9 --- /dev/null +++ b/STAT6101/Assignment_1b.Rmd @@ -0,0 +1,27 @@ +--- +title: "Assignment 1b" +author: "Satvik Saha" +date: "`r Sys.Date()`" +output: + pdf_document: default +--- + +```{r setup, include=FALSE} +knitr::opts_chunk$set(echo = TRUE) +``` + +## Answer 1 + +(a) The three challenges of statistical inference^[As per _Regression and Other Stories (Gelman, Hill, Vehtari)_] are as follows. + (i) _Generalizing from a sample to the population_. + (ii) _Generalizing from the treatment group to the control group_. + (iii) _Generalizing from the observed measurements to the underlying construct_. + +(b) The data and examples from the textbook are available at [https://avehtari.github.io/ROS-Examples/examples.html](https://avehtari.github.io/ROS-Examples/examples.html). + + +## Answer 2 + +(a) Consider the problem of trying to gauge the (relative) popularity of different chess players, by examining social media interaction. By sampling from social media posts or users, we can only access a population of chess enthusiasts _who use social media_. It is difficult to generalize to the population of chess enthusiasts as a whole; it is conceivable that the opinions of older chess enthusiasts (who may not use social media as frequently) will be underrepresented. +(b) Consider the problem of determining which color (or design) in an advertisement is most effective. If two competing designs are tested against two groups of people, there are a lot of adjustments that have to be made to account for differences between the groups, such as demand for the advertised item (perhaps affected by income, presence of competing brands, etc) or modes of advertisement. +(c) Consider the problem of ranking countries according to some 'happiness index'. Of course, the notion of _happiness_ is quite vague and difficult to pin down via reasonable measurements. The World Happiness Index uses factors such as GDP per capita, life expectancy, and perceptions of corruption, to extrapolate some underlying sense of national happiness. \ No newline at end of file diff --git a/STAT6101/Assignment_1b.pdf b/STAT6101/Assignment_1b.pdf new file mode 100644 index 0000000..27c6683 Binary files /dev/null and b/STAT6101/Assignment_1b.pdf differ diff --git a/STAT6101/Assignment_2a.Rmd b/STAT6101/Assignment_2a.Rmd new file mode 100644 index 0000000..4e050c1 --- /dev/null +++ b/STAT6101/Assignment_2a.Rmd @@ -0,0 +1,125 @@ +--- +title: "Assignment 2a" +author: "Satvik Saha" +date: "`r Sys.Date()`" +output: + pdf_document: default +--- + +```{r setup, include=FALSE} +knitr::opts_chunk$set(echo = TRUE) +knitr::opts_chunk$set(fig.pos = "!H", out.extra = "") +``` + +## Answer 1 + +(a) +```{r 1a} +print(seq(0, 20, by = 0.2)) +``` + +(b) +```{r 1b} +print(runif(1, min = 0, max = 10)) +``` + +(c) +```{r 1c} +print(runif(10, min = 0, max = 10)) +``` + + +## Answer 2 + +(a) +```{r 2a} +a <- c("Magnus Carlsen", "Hilary Hahn", "Linus Torvalds", "Persi Diaconis") +``` + +(b) +```{r 2b} +sample(a, 1) +``` + +(c) +```{r 2c} +x <- seq(0, 10, by = 0.5) +y <- sqrt(x) +plot(x, y) + +``` + +(d) +```{r 2d} +x <- seq(0, 10, length.out = 500) +y <- sqrt(x) +plot(x, y, type = "l") + +``` + +(e) +```{r 2e} +x <- seq(0, 20, length.out = 500) +y <- data.frame( + y1 = sqrt(x), + y2 = 2.5 + sqrt(x) +) +matplot(x, y, type = "l", col = c("blue", "red"), lty = 1) +``` + + +## Answer 3 + +![Answer 3(a)](2a3a.jpg){width=350px} +![Answer 3(b)](2a3b.jpg){width=350px} + +## Research homework assignment +Research homework assignment + +Suppose that $X$ and $Y$ are independent (real) random variables admitting +densities $f_X$ and $f_Y$, and let $Z = X/Y$. +We will say that $Z$ has Cauchy tails when $f_Z (z) \sim C/z^2$ as $|z| \to +\infty$ for some $C > 0$. + +**Proposition 1:** Suppose that $\mathbb{E}[|X|] < \infty$, and that $f_Y$ is bounded. +If $f_Y$ is continuous at $0$ with $f_Y(0) > 0$, then $Z = X/Y$ has Cauchy tails with $$ + f_Z(z) \sim \frac{f_Y(0) \:\mathbb{E}[|X|]}{z^2} \quad\text{as } |z| \to \infty. +$$ +_Proof:_ Observe that the density $f_Z$ of $Z$ is given by $$ + f_Z (z) = \int_\mathbb{R} |y| f_X(z y) f_Y(y) \:dy + = \frac{1}{z^2} \int_\mathbb{R} |x| f_X(x) f_Y\left(\frac{x}{z}\right) \:dx. +$$ +This can be seen by applying change of variables on $(X, Y)$ using the map +$(x, y) \mapsto (x/y, y)$, whose inverse is $(z, y) \mapsto (z y, y)$, and computing +the marginal. + +Let $f_Y < M$, so $$ + |x| f_X(x) f_Y\left(\frac{x}{z}\right) < |x| f_X(x) M \in L^1(\mathbb{R}) +$$ via $\mathbb{E}[|X|] < \infty$. +By the Dominated Convergence Theorem, we have $$ + \lim_{z \to \infty} z^2 f_Z(z) + = \lim_{z \to \infty} \int_\mathbb{R} |x| f_X(x) f_Y\left(\frac{x}{z}\right) \:dx + = \int_\mathbb{R} |x| f_X (x) f_Y(0) \:dx + = f_Y(0) \:\mathbb{E}[|X|]. \tag*{$\square$} +$$ + +_Remark:_ In the special case that $X, Y \sim N(0, 1)$, we have $X/Y \sim \text{Cauchy}(0, 1)$. + +Note that Proposition 1 does not cover situations such as $Y \sim \text{Uniform}(0, 1)$. +The continuity assumption on $f_Y$ can be relaxed slightly by dealing with the left and right tails of $Z$ separately. + +**Proposition 2:** Suppose that $\mathbb{E}[|X|] < \infty$, and that $f_Y$ is bounded. +If $f_Y$ has both left and right limits at $0$, then $Z = X/Y$ has a Cauchy right tail with $$ + f_Z(z) \sim \frac{f_Y(0^-) \:\mathbb{E}[X^-] + f_Y(0^+)\:\mathbb{E}[X^+]}{z^2} \quad\text{as } z \to +\infty, +$$ +and a Cauchy left tail with $$ + f_Z(z) \sim \frac{f_Y(0^+) \:\mathbb{E}[X^-] + f_Y(0^-)\:\mathbb{E}[X^+]}{z^2} \quad\text{as } z \to -\infty. +$$ + +_Proof:_ Following the same argument as in Proposition 1, we use the Dominated Convergence Theorem on $$ + z^2 f_Z(z) + = \int_{-\infty}^0 |x| f_X(x) f_Y\left(\frac{x}{z}\right) \:dx + + \int_0^{+\infty} |x| f_X(x) f_Y\left(\frac{x}{z}\right) \:dx. \tag*{$\square$} +$$ + +_Remark:_ Note that $Z = (1/Y) / (1/X)$, so Proposition 2 has an analogue which demands $\mathbb{E}[1/|Y|] < \infty$ and that the density of $1/X$ have both left and right limits at $0$. \ No newline at end of file diff --git a/STAT6101/Assignment_2a.pdf b/STAT6101/Assignment_2a.pdf new file mode 100644 index 0000000..ff90d3c Binary files /dev/null and b/STAT6101/Assignment_2a.pdf differ diff --git a/STAT6101/Assignment_2b.Rmd b/STAT6101/Assignment_2b.Rmd new file mode 100644 index 0000000..283c9d1 --- /dev/null +++ b/STAT6101/Assignment_2b.Rmd @@ -0,0 +1,50 @@ +--- +title: "Assignment 2b" +author: "Satvik Saha" +date: "`r Sys.Date()`" +output: + pdf_document: default +--- + +```{r setup, include=FALSE} +knitr::opts_chunk$set(echo = TRUE) +``` + +## Answer 1 + +```{r 1} +v1 <- rep(1, 10) +v2 <- 1:10 +v3 <- v2^2 + +X <- rbind(v1, v2, v3) +``` + +(a) For equal weights, the weighted average is just the usual simple average. +```{r 1a} +colMeans(X) +``` + +(b) +```{r 1b} +w <- c(1, 2, 3) +colSums(X * w) / sum(w) +``` + + +## Answer 2 + +(a) Number of games won by a chess player who has played 20 games, with a probability of 30% of winning each game. +```{r 2a} +rbinom(1, 20, 0.3) +``` + +(b) Number of games won by a couple of chess players who have played 20 games (not against each other). The first has a probability of 30% of winning each game, while the second has a probability of 40% of winning each game. +```{r 2b} +rbinom(2, 20, c(0.3, 0.4)) +``` + +(c) Number of games won by a couple of chess players. The first has played 30 games with a probability of 30% of winning each game, while the second has played 20 games with a probability of 40% of winning each game. +```{r 2c} +rbinom(2, c(30, 20), c(0.3, 0.4)) +``` \ No newline at end of file diff --git a/STAT6101/Assignment_2b.pdf b/STAT6101/Assignment_2b.pdf new file mode 100644 index 0000000..36d0956 Binary files /dev/null and b/STAT6101/Assignment_2b.pdf differ diff --git a/STAT6101/Assignment_3a.Rmd b/STAT6101/Assignment_3a.Rmd new file mode 100644 index 0000000..433cd20 --- /dev/null +++ b/STAT6101/Assignment_3a.Rmd @@ -0,0 +1,269 @@ +--- +title: "Assignment 3a" +author: "Satvik Saha" +date: "`r Sys.Date()`" +output: + pdf_document: default +--- + +```{r setup, include=FALSE} +knitr::opts_chunk$set(echo = TRUE) +knitr::opts_chunk$set(fig.pos = "!H", out.extra = "") +``` + +## Answer 1 + +(a) We approximate the 95% confidence interval for the proportion $p$ who answer 'Yes' using a $\pm z_{0.025} \text{ s.e.}$ interval around the estimate $\hat{p} = y / n$. +```{r 1a} +n <- 1500 +y <- 750 + +p.hat <- y / n +se <- sqrt(p.hat * (1 - p.hat) / n) +p.ci <- p.hat + qnorm(c(0.025, 0.975)) * se + +p.ci +``` + +(b) +```{r 1b} +n <- 1500 +y <- 900 + +p.hat <- y / n +se <- sqrt(p.hat * (1 - p.hat) / n) +p.ci <- p.hat + qnorm(c(0.025, 0.975)) * se + +p.ci +``` + +(c) +```{r 1c} +n <- 10 +y <- 6 + +p.hat <- y / n +se <- sqrt(p.hat * (1 - p.hat) / n) +p.ci <- p.hat + qnorm(c(0.025, 0.975)) * se + +p.ci +``` + + +## Answer 2 + +We switch to using an estimator of the form $\hat{p} = (y + 2) / (n + 4)$. +```{r 2} +n <- 50 +y <- 0 + +p.hat <- (y + 2) / (n + 4) +se <- sqrt(p.hat * (1 - p.hat) / n) +p.ci <- p.hat + qnorm(c(0.025, 0.975)) * se + +p.ci +``` +Thus, we report a 95% confidence interval of $[0, 0.09]$. + + +## Answer 3 + +Let $\ell = 0.15$ be the national fraction of Latinos. Also let $p_L$ be the probability of a 'Yes' response from a Latino, $p_O$ from others. Further assume that $p_L, p_O \approx 0.5$. We model the two options for the survey as follows. + +(i) Let each response be recorded as $(x_i, z_i)$, where $x_i$ is $1$ for 'Yes' and $0$ for 'No', and $z_i$ is $1$ for Latino and $0$ for other. Then, we have $$ + x_i\mid z_i \sim \text{Bernoulli}(p_L^{z_i}p_O^{1 - z_i}), \qquad + z_i \sim \text{Bernoulli}(\ell). +$$ +It follows that $$ + x_i \sim \text{Bernoulli}(p), \qquad + p = \ell p_L + (1 - \ell)p_O. +$$ +Thus, $p$ denotes the national average. +Setting $y = \sum_i x_i$, the number of 'Yes' responses from a simple random sample of $n = 1000$ Americans is $$ + y \sim \text{Binomial}(n, p). +$$ +The number of responses from Latinos is $n_L = \sum_i z_i$, others is $n_O = \sum_i (1 - z_i) = n - n_L$. +Also, the number of 'Yes' responses from Latinos is $y_L = \sum_i x_i z_i$, others is $y_O = \sum_i x_i(1 - z_i) = y - y_L$. +We note that $y_L, y_O$ when conditioned on $n_L$ are independent; this model for $(n_L, n_O, y_L, y_O)$is equivalent to first drawing $n_L \sim \text{Binomial}(n, \ell)$, setting $n_O = n - n_L$, then drawing (independently) $$ + y_L \mid n_L \sim \text{Binomial}(n_L, p_L), \qquad + y_O \mid n_L \sim \text{Binomial}(n_O, p_O). +$$ +With this, the difference $p_L - p_O$ between Latinos and others is estimated by $y_L/n_L - y_O/n_O$, and the national average $p$ is estimated as $y / n$. + +(ii) The number of Latinos sampled is $n_L = 300$, non-Latinos is $n_O = 700$, for a total of $n = n_L + n_O = 1000$ responses. The number of 'Yes' responses $y_L$ from Latinos and $y_O$ from others is modeled as $$ + y_L \sim \text{Binomial}(n_L, p_L), \qquad + y_O \sim \text{Binomial}(n_O, p_O). +$$ +The difference $p_L - p_O$ between Latinos and others is estimated as $y_L/n_L - y_O/n_O$, and the national average $p$ is estimated as $\ell y_L/n_L + (1 - \ell)y_O/n_O$. + + +With this, we can now compare the two options. + +(a) Option (ii) gives more accurate comparisons between Latinos and others, and option (i) gives more accurate national population estimates. + +(b) First, examine the national average estimates. In option (i), we simply have $\text{var}(y/n) = p(1 - p) / n \approx 1/4n$. In option (ii), we have $$ + \text{var}\left(\frac{\ell y_L}{n_L} + \frac{(1 - \ell)y_O}{n_O}\right) = \frac{\ell^2 p_L(1 - p_L)}{n_L} + \frac{(1 - \ell)^2 p_O(1 - p_O)}{n_O} \approx \frac{\ell^2}{4n_L} + \frac{(1 - \ell)^2}{4n_O}. +$$ +``` {r 3a} +n <- 1000 +n_L <- 300 +n_O <- 700 +ell <- 0.15 + +print(sqrt(1/(4 * n))) +print(sqrt(1/4 * (ell^2 / n_L + (1 - ell)^2 / n_O))) +``` +Thus, option (i) gives a tighter estimate of the national average opinion. + +Next, examine the comparison between the Latino response and the others. In option (i), observe that $$ + \text{var}\left(\frac{y_L}{n_L} - \frac{y_O}{n_O}\right) = \mathbb{E}\left[\text{var}\left(\frac{y_L}{n_L} - \frac{y_O}{n_O} \,\Bigg|\,n_L\right)\right] + \text{var}\left(\mathbb{E}\left[\frac{y_L}{n_L} - \frac{y_O}{n_O} \,\Bigg|\,n_L\right]\right). +$$ +Note that the second term vanishes; the conditional expectation there is just the constant $p_L - p_O$. This leaves us with $$ + \mathbb{E}\left[\frac{p_L (1 - p_L)}{n_L} + \frac{p_O (1 - p_O)}{n_O}\right] \approx \mathbb{E}\left[\frac{1}{4n_L} + \frac{1}{4(n - n_L)}\right] = \mathbb{E}\left[\frac{n}{4n_L(n - n_L)}\right]. +$$ +Recall that $n_L \sim \text{Binomial}(n, \ell)$; we will approximate the above via simulation. + +In option (ii), we simply have $$ + \text{var}\left(\frac{y_L}{n_L} - \frac{y_O}{n_O}\right) = \frac{p_L(1 - p_L)}{n_L} + \frac{p_O(1 - p_O)}{n_O} \approx \frac{1}{4n_L} + \frac{1}{4n_O} = \frac{n}{4 n_L (1 - n_L)}. +$$ +``` {r 3b} +n <- 1000 +n_L <- 300 +n_O <- 700 +ell <- 0.15 + +n_L.sim <- rbinom(1000000, 1000, ell) + +print(sqrt(mean(n/(4 * n_L.sim * (n - n_L.sim))))) +print(sqrt(1/4 * (1 / n_L + 1 / n_O))) +``` +Thus, option (ii) gives a tighter estimate for the difference in response between Latinos and others. + + + +## Research homework assignment + +We generate the data $\theta_j \sim t_5(0, 0.1)$ and $\hat{\theta}_j \mid \theta_j \sim N(\theta_j, \sigma_j)$ for $1 \leq j \leq J$ as follows. + +```{r generate} +generate.theta <- function( + J, + sigma, + df = 5, + scale = 0.1 +) { + theta <- rt(J, df = df) * scale + theta.hat <- rnorm(J, mean = theta, sd = sigma) + return(list( + theta = theta, + theta.hat = theta.hat + )) +} +``` +With this, we construct the suggested strategies, referred to as "Everything", "Nothing", "Positive", and "Significant" (in order). Each strategy takes a $J$-vector of $(\hat{\theta}_j)$ and returns a binary $J$-vector indicating whether or not to implement each intervention. +```{r strategies} +strategy.everything <- function(theta.hat, sigma) { + return(rep(1, length(theta.hat))) +} + +strategy.nothing <- function(theta.hat, sigma) { + return(rep(0, length(theta.hat))) +} + +strategy.positive <- function(theta.hat, sigma) { + return(as.numeric(theta.hat > 0)) +} + +z.alpha <- qnorm(0.95) +strategy.significant <- function(theta.hat, sigma) { + return(as.numeric(theta.hat / sigma > z.alpha)) +} +``` +The gain for a strategy $\hat{\theta} \mapsto \delta(\hat{\theta})$ is simply $\sum_j x_j \theta_j \delta(\hat{\theta}_j)$. +The ideal strategy is one that will implement an intervention _if and only if_ $\theta_j > 0$. +Observe that the "Nothing" strategy will always give a gain of $0$; with this in mind, we will omit this strategy in further discussion. +```{r strategies.store} +strategies <- c( + strategy.everything, + # strategy.nothing, + strategy.positive, + strategy.significant +) +strategies.names <- c( + "Everything", + # "Nothing", + "Positive", + "Significant" +) +``` +We loop our simulation $1000$ times, for $J = 10, 10^2, 10^3, 10^4$ and for $\sigma = 0.05, 0.2$. +```{r simulate} +x <- 1000 +gains <- data.frame() +runs <- 1000 +for (J in c(10, 100, 1000, 10000)) { + for (sigma in c(0.05, 0.2)) { + for (i in 1:runs) { + d <- generate.theta(J, sigma = sigma) + g <- c(J, sigma) + for (strategy in strategies) { + gain <- sum(x * d$theta * strategy(d$theta.hat, sigma)) + g <- c(g, gain) + } + gains <- rbind(gains, g) + } + } +} +colnames(gains) <- c("J", "sigma", strategies.names) +``` +The expected gain in sales for each of these strategies can be estimated by the mean gain over the $1000$ runs, as follows. +```{r gains} +suppressMessages(library(tidyr)) +suppressMessages(library(dplyr)) + +gains <- gather(gains, key = "Strategy", value = "Gains", -J, -sigma) +gains %>% + group_by(sigma, J, Strategy) %>% + summarize(Mean = mean(Gains)) %>% + ungroup() %>% + pivot_wider(names_from = Strategy, values_from = Mean) +``` +The variation in gain in sales over multiple runs can be better visualized using the following histograms. +```{r histograms, echo = T, results = 'hide'} +library(ggplot2) + +pdf("3a_rha.pdf", width = 16, height = 8) +ggplot(gains, aes(Gains)) + + geom_histogram( + aes(color = Strategy, fill = Strategy), + alpha = 0.2, + position = "identity" + ) + + facet_grid(rows = vars(sigma), cols = vars(J), scales = "free_x") +dev.off() +``` + +![Distributions of gain in sales by strategy (color), $J$ (columns), $\sigma$ (rows).](3a_rha.pdf) + +It seems that on average, the "Positive" strategy performs better than the "Significant" strategy, which in turn performs better than the "Everything" and "Nothing" strategies. Both the "Everything" and "Nothing" strategies both must have an expected gain of zero, the "Everything" strategy simply has more variance. The difference between the "Positive" and "Significant" strategies becomes more apparent with increasing $J$. + +The distribution of gains $\sum_j x_j\theta_j\delta(\hat{\theta}_j)$ for a strategy $\delta$ is asymptotically normal via the Central Limit Theorem; note that the $\theta_j\delta(\hat{\theta}_j)$ are independent and identically distributed, with finite second moments. + +Note that the "Significant" strategy $\delta_s$ is more demanding than the "Positive" strategy $\delta_p$, in the sense that $\delta_s \leq \delta_p$. By being more conservative, the "Significant" strategy seems to avoid losses (when $\theta_j < 0$), but also discards potentially small gains (when $\theta_j > 0$ is small). This may help explain why this performs poorer than the "Positive" strategy. + +By increasing $\sigma_j$, the observed quantity $\hat{\theta}_j$ begins offering less information about $\theta$. Thus, the "Positive" and "Significant" strategies begin suffering in performance. + +In general, a strategy of the form $\delta_c(\hat{\theta}) = \mathbf{1}(\hat{\theta}/\sigma > c)$ for some cutoff $c$ will have an expected gain of the form $$ + \mathbb{E}[\theta \,\delta_c(\hat{\theta})] = \mathbb{E}[\theta \,\mathbb{P}(\hat{\theta} > c\sigma \mid \theta)] = \mathbb{E}\left[\theta\,\Phi\left(\frac{\theta}{\sigma} - c\right)\right], +$$ which is difficult to calculate analytically (but has been estimated here via simulation). Of course, this quantity goes to $0$ as $c \to \infty$ (DCT). +```{r expectation} +sigma <- 0.05 +cutoffs <- seq(-3, 3, length.out = 100) +means <- rowMeans(replicate(10000, { + theta <- rt(100, df = 5) * 0.1 + theta * pnorm(theta / sigma - cutoffs) +})) +plot(cutoffs, means) +``` + +It seems that $c = 0$ is indeed an optimal cutoff. \ No newline at end of file diff --git a/STAT6101/Assignment_3a.pdf b/STAT6101/Assignment_3a.pdf new file mode 100644 index 0000000..ef6430c Binary files /dev/null and b/STAT6101/Assignment_3a.pdf differ diff --git a/STAT6101/Assignment_3b.Rmd b/STAT6101/Assignment_3b.Rmd new file mode 100644 index 0000000..7f08944 --- /dev/null +++ b/STAT6101/Assignment_3b.Rmd @@ -0,0 +1,129 @@ +--- +title: "Assignment 3b" +author: "Satvik Saha" +date: "`r Sys.Date()`" +output: + pdf_document: default +--- + +```{r setup, include=FALSE} +knitr::opts_chunk$set(echo = TRUE) +``` + +## Answer 1 + +(a) The number of shots made is simply a $\text{Binomial}(10, 0.40)$ random variable. +```{r 1a} +rbinom(1, 10, 0.40) +``` + +(b) Each shot behaves like a $\text{Bernoulli}(p_i)$ random variable, with $p_i = i/10$. +```{r 1b} +p <- seq(0.10, 1.00, by = 0.10) +sum(sapply(p, function(p.i) rbinom(1, 1, p.i))) +``` + + +## Answer 2 + +Using the arguments from Assignment 3a, Problem 3, we take a simple random sample of $n$ people, of which $n_m \sim \text{Binomial}(n, f_m)$ will be men, where $f_m \approx 0.5$ is the proportion of men in voting population. +Then, the number of men $y_m$ and women $y_w$ supporting the candidate are modeled as $$ + y_m \mid n_m \sim \text{Binomial}(n_m, p_m), \qquad + y_w \mid n_m \sim \text{Binomial}(n_w, p_w), +$$ where $n_w = n - n_m$, and $p_m, p_w$ are the population proportions of men and women supporting the candidate. +We estimate the gender gap $\delta = p_m - p_w$ via $$ + \hat{\delta} = \begin{cases} + y_m/n_m - y_w/n_w, &\text{if } n_m, n_w > 0, \\ + 0, &\text{otherwise}. + \end{cases} +$$ +This estimator suffers for $n_m, n_w = 0$; we set these aside as very low probability events. +As before, we can compute $$ +\begin{aligned} + \text{var}(\hat{\delta}) + &= \mathbb{E}\left[\left(\frac{p_m(1 - p_m)}{n_m} + \frac{p_w(1 - p_w)}{n_w}\right)\mathbf{1}(n_m \notin \{0, n\})\right] + \text{var}\left((p_m - p_w)\mathbf{1}(n_m \notin \{0, n\})\right) \\ + &\leq \mathbb{E}\left[\frac{n}{4n_m(n - n_m)}\mathbf{1}(n_m \notin \{0, n\})\right] + (p_m - p_w)^2 (f_m^n+ f_w^n)(1 - (f_m^n+ f_w^n)) \\ + &\leq \mathbb{E}\left[\frac{n}{4n_m(n - n_m)}\mathbf{1}(n_m \notin \{0, n\})\right] + (f_m^n+ f_w^n) \\ + &\approx \mathbb{E}\left[\frac{n}{4n_m(n - n_m)}\mathbf{1}(n_m \notin \{0, n\})\right], +\end{aligned} +$$ where we discard the last term $f_m^n + f_w^n \approx 1/2^{n - 1}$. +We simulate +``` {r 2} +sd.approx <- function(n, f_m = 0.5, sims = 10000) { + n_m <- rbinom(sims, n, f_m) + sqrt(mean(n / (4 * n_m * (n - n_m)))) +} +n <- 350:450 +se <- sapply(n, function(k) sd.approx(k)) +print(n[which.max(se <= 0.05)]) +plot(n, se) +``` + +Thus, we need to poll a little over $400$ people to ensure that the standard error is less than $5$ percentage points. + + +## Answer 3 + +Let $X \sim \text{Binomial}(20, 0.30)$ and $Y \sim \text{Binomial}(20, 0.40)$ be independent, denoting the number of shots made by the two students. +We have $$ + \mathbb{P}(X = i, Y = j) = \mathbb{P}(X = i) \mathbb{P}(Y = j) = \binom{20}{i}\binom{20}{j} 0.3^i 0.7^{20 - i} 0.4^j 0.6^{20 - j}. +$$ +Then, $$ + \mathbb{P}(X < Y) = \sum_{i = 0}^{20} \sum_{j = i + 1}^{20} \mathbb{P}(X = i, Y = j). +$$ +This can be computed as approximately $69.3\%$, as follows. +``` {r 3} +probs.greater <- sapply(0:20, function(i) + sapply((i + 1):20, function(j) + dbinom(i, 20, 0.30) * dbinom(j, 20, 0.40) + ) +) +sum(unlist(probs.greater)) +``` + + +## Answer 4 + +We will say that we have a good chance of distinguishing the shooters given $n$ shots each if the probability of the better shooter scoring higher is at least $1 - \alpha$. +We choose $\alpha = 0.05$. +```{r 4} +p.distinguish <- function(n, p1, p2) { + probs.greater <- sapply(0:n, function(i) + sapply((i + 1):n, function(j) + dbinom(i, n, p1) * dbinom(j, n, p2) + ) +) + sum(unlist(probs.greater)) +} + +n <- 100:150 +probs <- sapply(n, function(k) p.distinguish(k, 0.30, 0.40)) +plot(n, probs) +abline(h = 0.95) +``` + +With this, we demand around $n = 140$ shots. + +We could also have tried using the normal approximations for independent $X \sim \text{Binomial}(n, p)$ and $Y \sim \text{Binomial}(n, q)$ to obtain $$ + X - Y \overset{a}{\sim} N\left(n(p - q),\, n(p(1 - p) + q(1 - q))\right), +$$ so $$ + P(X < Y) \approx \Phi\left(\frac{\sqrt{n}(q - p)}{\sqrt{p(1 - p) + q(1 - q)}}\right). +$$ +``` {r 4 normal} +p.distinguish.normal <- function(n, p1, p2) { + pnorm(sqrt(n) * (p2 - p1) / sqrt(p1 * (1 - p1) + p2 * (1 - p2))) +} +n <- 100:200 +probs <- sapply(n, function(k) p.distinguish(k, 0.30, 0.40)) +probs.normal <- sapply(n, function(k) p.distinguish.normal(k, 0.30, 0.40)) +plot(n, probs) +lines(n, probs.normal) +abline(h = 0.95) +``` + +It seems that the normal approximation underestimates $n$ a little. + +We could also verify our answer $n \approx 140$ via simulation. +``` {r 4 simulate} +mean(rbinom(10000, 140, 0.3) < rbinom(10000, 140, 0.4)) +``` \ No newline at end of file diff --git a/STAT6101/Assignment_3b.pdf b/STAT6101/Assignment_3b.pdf new file mode 100644 index 0000000..fbb0c9e Binary files /dev/null and b/STAT6101/Assignment_3b.pdf differ diff --git a/STAT6101/Assignment_4a.Rmd b/STAT6101/Assignment_4a.Rmd new file mode 100644 index 0000000..dfc10f4 --- /dev/null +++ b/STAT6101/Assignment_4a.Rmd @@ -0,0 +1,133 @@ +--- +title: "Assignment 4a" +author: "Satvik Saha" +date: "`r Sys.Date()`" +output: + pdf_document: default +--- + +```{r setup, include=FALSE} +knitr::opts_chunk$set(echo = TRUE) +knitr::opts_chunk$set(fig.pos = "!H", out.extra = "") +``` + +## Answer 1 + +(a) +``` {r 1a, message = FALSE} +n <- 100 +a <- 1 # intercept +b <- 2 # slope +sigma <- 3 # residual standard deviation +x <- runif(n, min = 0, max = 4) +y <- a + b*x + sigma * rnorm(n) +df <- data.frame(x, y) + +library(rstanarm) +fit.y <- stan_glm(y ~ x, data = df, refresh = 0) +print(fit.y) +``` + +To check whether or not the true coefficients lie within one standard deviation of the estimates, we do the following. +``` {r 1a check} +a.hat <- coef(fit.y)[1] +b.hat <- coef(fit.y)[2] +a.se <- se(fit.y)[1] +b.se <- se(fit.y)[2] + +abs(a.hat - a) < a.se +abs(b.hat - b) < b.se +``` + +(b) +``` {r 1b} +plot(x, y, main = "Data and fitted regression line") +abline(a.hat, b.hat) +x.bar <- mean(x) +text(2.5, -1, paste("y = ", round(a.hat, 2), " + ", round(b.hat, 2), "*x"), adj = 0) +``` + + +## Answer 2 + +(a) Following the discussion in ROS about regression to the mean dealing with exam scores, we guess that while most pairs $(x, y)$ of scores will follow the line $(x, 2x)$, the regression will yield coefficients of the form $a = 25$, $b = 1$, $\sigma = 10$. + +(b) We guess that there is a shift from Democratic to Republican votes as age increases, but with the discrepancy being $60\%$-$40\$$ at most. +The independent vote is estimated to be very little, perhaps simply proportional to the age distribution (any non-zero effect of age here is perhaps too small to illustrate). +With this, we guess that our regression line passes through $(20, -0.2)$ and $(80, 0.2)$. +Thus, $a = -1/3$, $b = 1/150$, $\sigma = 1$. + +![Answer 2(a)](4a2a.png){width=350px} +![Answer 2(b)](4a2b.png){width=350px} + +## Answer 3 + +(a) +```{r 3a} +dbinom(3, 10, 0.40) +``` + +(b) +```{r 3b} +shots <- function(n, p) rbinom(1, n, p) +mean(replicate(10000, shots(10, 0.40) == 3)) +``` + + + +## Research homework assignment + +We take a first look at our height and earnings data. + +```{r rha data} +earnings <- read.csv("earnings.csv") +plot(earnings$height, earnings$earn) +``` + +Around $10\%$ of people have $0$ earnings. +Note that a simple transformation of the form $\log(1 + y)$ places these data points in an isolated pile at the bottom. +```{r rha zero} +mean(earnings$earn == 0) +plot(earnings$height, log(1 + earnings$earn)) +``` + +Instead, we look at the transformation $\log(A + y)$. +Temporarily, we can also look at $\log(1 + y/A)$, which differs from $\log(A + y)$ only by a constant $\log(A)$. +This also sends zeroes to zeroes. +In this new settings, we may interpret $A$ as a scaling factor (which also helps make $y/A$ dimensionless). +With this, we suggest using $A = \text{MAD}(\mathbf{y})$. + +```{r rha scaled} +A <- mad(earnings$earn) +print(A) +plot(earnings$height, log(1 + earnings$earn/A)) +``` + +We can fit this model as follows. +The coefficients can be read off of the `stan_glm` output. + +```{r rha fit} +x <- earnings$height +y <- earnings$earn +y.l <- log(A + y) +df <- data.frame(x, y.l) + +fit.y.l <- stan_glm(y.l ~ x, data = df, refresh = 0) +print(fit.y.l) +plot(x, y.l, xlab = "height", ylab = "log(A + earnings)") +abline(coef(fit.y.l)[1], coef(fit.y.l)[2]) +``` + +We can also take a look at the residuals, which are approximately normally distributed. + +```{r rha residuals} +residuals <- y.l - (coef(fit.y.l)[1] + coef(fit.y.l)[2] * x) +shapiro.test(residuals) +R2 <- 1 - sum(residuals^2) / sum((y.l - mean(y.l))^2) +print(R2) +hist(residuals, breaks = 16) +``` + +It is difficult to suggest an appropriate scaling factor $A$ for $y$ without resorting to some measure of dispersion such as the Median Absolute Deviation or standard deviation. +Choosing small values of $A$ makes the problem of separation between the $y = 0$ values from the rest of the data worse. +Choosing large values of $A$ flattens the bulk of the data far too much and stretches out the top of the plot. \ No newline at end of file diff --git a/STAT6101/Assignment_4a.pdf b/STAT6101/Assignment_4a.pdf new file mode 100644 index 0000000..263b3c5 Binary files /dev/null and b/STAT6101/Assignment_4a.pdf differ diff --git a/STAT6101/Assignment_4b.Rmd b/STAT6101/Assignment_4b.Rmd new file mode 100644 index 0000000..e4cd14d --- /dev/null +++ b/STAT6101/Assignment_4b.Rmd @@ -0,0 +1,92 @@ +--- +title: "Assignment 4b" +author: "Satvik Saha" +date: "`r Sys.Date()`" +output: + pdf_document: default +--- + +```{r setup, include=FALSE} +knitr::opts_chunk$set(echo = TRUE) +knitr::opts_chunk$set(fig.pos = "!H", out.extra = "") +``` + +## Answer 1 + +(a) +``` {r 1a, message = FALSE} +library(rstanarm) + +gen.fit.linear <- function(n, a, b, sigma, x.lo, x.hi) { + x <- runif(n, min = x.lo, max = x.hi) + y <- a + b*x + sigma * rnorm(n) + df <- data.frame(x, y) + + fit.y <- stan_glm(y ~ x, data = df, refresh = 0) + a.hat <- coef(fit.y)[1] + b.hat <- coef(fit.y)[2] + a.se <- se(fit.y)[1] + b.se <- se(fit.y)[2] + + return(list( + fit = fit.y, + slope.1.se = abs(b.hat - b) < b.se + )) +} + +``` + + +(b) +``` {r 1b} +gen.fit.linear( + n = 50, + a = 10, + b = -20, + sigma = 30, + x.lo = 0, + x.hi = 1 +) +``` + + + +## Answer 2 + +(a) The regression model $y_i = a + \epsilon_i$ involves minimizing the residual sum of squares $\text{RSS} = \sum_{i = 1}^n (y_i - a)^2$, which is solved by $\hat{a} = \frac{1}{n}\sum_{i = 1}^n y_i = \bar{y}$. +This is easily seen via \[ + \text{RSS} = \sum_{i = 1}^n (y_i - \bar{y})^2 + n(\bar{y} - a)^2. +\] + +``` {r 2a, message = FALSE} +fit.scores <- function(scores) { + fit.y <- stan_glm(test_scores ~ 1, data = scores, refresh = 0) + a.hat <- coef(fit.y)[1] + + return(list( + fit = fit.y, + a.hat = a.hat + )) +} +``` + +``` {r 2a gen} +ugrad <- data.frame( + level = 1, + test_scores = 50 + 10 * rnorm(10) +) +grad <- data.frame( + level = 2, + test_scores = 60 + 15 * rnorm(10) +) +scores <- rbind(ugrad, grad) +head(scores[sample(nrow(scores)), ]) +``` + +``` {r 2a check} +mean(scores$test_scores) + +fit.scores(scores) +``` + +Of course, `stan_glm` goes beyond simple linear regression, with priors and regularization, but the point stands. \ No newline at end of file diff --git a/STAT6101/Assignment_4b.pdf b/STAT6101/Assignment_4b.pdf new file mode 100644 index 0000000..45d5e3a Binary files /dev/null and b/STAT6101/Assignment_4b.pdf differ diff --git a/STAT6101/Assignment_5a.Rmd b/STAT6101/Assignment_5a.Rmd new file mode 100644 index 0000000..7771f61 --- /dev/null +++ b/STAT6101/Assignment_5a.Rmd @@ -0,0 +1,105 @@ +--- +title: "Assignment 5a" +author: "Satvik Saha" +date: "`r Sys.Date()`" +output: + pdf_document: default +--- + +```{r setup, include=FALSE} +knitr::opts_chunk$set(echo = TRUE) +knitr::opts_chunk$set(fig.pos = "!H", out.extra = "") +``` + +## Answer 1 + +Consider simple linear regression with $3$ data points, where $\{x_i\}$ are equally spaced. +By shifting and scaling, we may consider the case $x_1 = -1, x_2 = 0, x_3 = 1$. +Then, the slope is given by $$ + \hat{b} = \frac{n\sum_{i = 1}^n x_i y_i - \sum_{i = 1}^n x_i \sum_{i = 1}^n y_i}{n\sum_{i = 1}^n x_i^2 - \left(\sum_{i = 1}^n x_i\right)^2} = \frac{y_3 - y_1}{2}. +$$ +This is independent of $y_2$! +Similarly, the intercept is given by $$ + \hat{a} = \frac{\sum_{i = 1}^n y_i \sum_{i = 1}^n x_i^2 - \sum_{i = 1}^n x_i \sum_{i = 1}^n x_iy_i}{n\sum_{i = 1}^n x_i^2 - \left(\sum_{i = 1}^n x_i\right)^2} = \frac{y_1 + y_2 + y_3}{6}. +$$ + +(a) The slope $b = (2 - 0) / 2 = 1$ (this is unaffected by the shift in $x$). +(b) The intercept can be alternatively calculated as the mean of $y_i - \hat{b}x_i$ (recall the discussion on regression on a constant), hence we calculate $a = (0 + 1 + 0)/3 = 1/3$. + +(c) Since the $x_i$'s are spaced by $50$ years, we scale our slope down, giving $b = (6 - 1.5)\times 10^9 / (2 \times 50) = 4.5 \times 10^7$ people per year. +For the intercept, we calculate the mean $a = (1.5 + 2.5 + 6)\times 10^9 / 3 - b\times1950 = (10/3 - 87.75) \times 10^9 \approx 84.42 \times 10^9$ people. + + + +## Answer 2 + +(a) We prepare the data as follows. +``` {r 2a load} +df <- read.table("hibbs.dat", header = TRUE) +df$more <- as.numeric(df$growth > 2.0) +head(df) +``` + +The average difference in vote share has a standard error which can be estimated by computing the variances in each group, then combining them. +``` {r 2a compute} +df.less <- df[df$more == 0, ] +df.more <- df[df$more == 1, ] + +diff.hat <- mean(df.more$vote) - mean(df.less$vote) +diff.se <- sqrt(sd(df.more$vote)^2/nrow(df.more) + sd(df.less$vote)^2/nrow(df.less)) + +diff.hat +diff.se +``` + +(b) We perform the linear fit using `lm` to eliminate the effect of priors, regularization, etc. +``` {r 2b} +diff.fit <- lm(vote ~ more, data = df) +summary(diff.fit) +``` +The estimate for the slope and its standard error agrees with our calculation precisely. + + + + +## Research homework assignment + +Consider the model $y_i \sim \theta + \epsilon_i$, with $\epsilon_i \overset{iid}{\sim} N(0, \sigma)$. +With just this setup, we may use the OLS estimate $\hat{\theta} = \bar{y} = \frac{1}{n}\mathbf{1}^\top \mathbf{y}$, hence our predictions are $\hat{\mathbf{y}} = \frac{1}{n}\mathbf{1}\mathbf{1}^\top \mathbf{y} = H\mathbf{y}$. +The effective number of parameters here becomes $\text{trace}(H) = 1$. +Note that $\sigma$ here is a nuisance parameter, which we are not interested in. +In the MLE setup, where both $\theta$ and $\sigma$ play a role, it would be natural to consider $2$ parameters. + +Now, add the restriction that $\theta \in (0, 1)$; perhaps this can be achieved by imposing a prior on $\theta$ supported on $[0, 1]$, say a uniform one. +With a prior $\pi(\sigma^2) \propto 1/\sigma^2$, we may compute the Bayes estimate for $\theta$, which under the squared error loss is the posterior mean of $\theta$, $$ + \hat{\theta}(\mathbf{y}) + = \frac{\displaystyle\int_0^1\int_0^\infty \theta \cdot (2\pi\sigma^2)^{-n/2} e^{-\sum_i (y_i - \theta)^2/2\sigma^2}\cdot (\sigma^2)^{-1} \:d\sigma^2\:d\theta}{\displaystyle\int_0^1\int_0^\infty (2\pi\sigma^2)^{-n/2} e^{-\sum_i (y_i - \theta)^2/2\sigma^2}\cdot (\sigma^2)^{-1} \:d\sigma^2\:d\theta} + = \frac{\displaystyle\int_0^1 \theta\cdot \left(1 + \frac{(\bar{y} - \theta)^2}{\frac{1}{n}\sum_i (y_i - \bar{y})^2}\right)^{-n/2} \:d\theta}{\displaystyle\int_0^1 \left(1 + \frac{(\bar{y} - \theta)^2}{\frac{1}{n}\sum_i (y_i - \bar{y})^2}\right)^{-n/2} \:d\theta}. +$$ +Thus, $\hat{\mathbf{y}} = \mathbf{1}\,\hat{\theta}(\mathbf{y})$. +To obtain the analogous version of effective number of parameters, we would need to compute $$ + n_{\text{eff}} = \sum_i \frac{\partial}{\partial y_i}\, \hat{\theta}(\mathbf{y}). +$$ +This setup does not admit nice computations! + +Another estimator involves simply clamping $\bar{y}$ within $(0, 1)$, via $$ + \hat{\theta}(\mathbf{y}) = \begin{cases} + 0, &\text{ if } \bar{y} < 0, \\ + \bar{y}, &\text{ if } \bar{y} \in [0, 1], \\ + 1, &\text{ if } \bar{y} > 0. + \end{cases} +$$ +With this interpretation, we have the awkward $$ + n_{\text{eff}} + = \sum_i \frac{\partial}{\partial y_i}\, \hat{\theta}(\mathbf{y}) + = \hat{\theta}(\mathbf{y}) = \begin{cases} + 1, &\text{ if } \bar{y} \in [0, 1], \\ + 0, &\text{ otherwise}. + \end{cases} +$$ +Of course, this kind of estimator that clamps $\bar{y}$ is very different from a regularized estimator, where $n_{\text{eff}}$ would be some positive number between $0$ and $1$. + +Intuitively, it ought to make sense that restricting $\theta$ to an interval, say $(-\epsilon, \epsilon)$, should reduce the number of effective parameters with decreasing $\epsilon$. +If this restriction is modeled using a uniform prior on $(-\epsilon, \epsilon)$, this would degenerate to a $\delta_0$ prior, which completely eliminates the role of the parameter $\theta$. +However, without a broader context with which to judge the 'amount of freedom a parameter enjoys', it becomes difficult to quantify this with actual numbers. +We may be able to make comparisons between models with restrictions of this kind, but this reasoning does not hold for more general priors. \ No newline at end of file diff --git a/STAT6101/Assignment_5a.pdf b/STAT6101/Assignment_5a.pdf new file mode 100644 index 0000000..10b20f4 Binary files /dev/null and b/STAT6101/Assignment_5a.pdf differ diff --git a/STAT6101/Assignment_5b.Rmd b/STAT6101/Assignment_5b.Rmd new file mode 100644 index 0000000..237f3eb --- /dev/null +++ b/STAT6101/Assignment_5b.Rmd @@ -0,0 +1,123 @@ +--- +title: "Assignment 5b" +author: "Satvik Saha" +date: "`r Sys.Date()`" +output: + pdf_document: default +--- + +```{r setup, include=FALSE} +knitr::opts_chunk$set(echo = TRUE) +knitr::opts_chunk$set(fig.pos = "!H", out.extra = "") +``` + +## Answer 1 + +``` {r 1 data, message = FALSE} +library(rstanarm) + +n <- 30 +x <- rnorm(n, mean = 6, sd = 2) +x <- pmax(pmin(x, 10), 0) +z <- sample(c(0, 1), n, replace = TRUE) +y <- x + 1.5 * (z - 0.5) + 0.5 * rnorm(n) +y <- pmax(pmin(y, 10), 0) +df <- data.frame(x = x, y = y, z = z) +plot(x, y, pch = z + 2) + +prior.x.sd <- 2.5 * sd(y) / sd(x) +``` + +(a) +``` {r 1a} +fit.a <- stan_glm( + y ~ x + z, + data = df, + refresh = 0 +) +fit.a +prior_summary(fit.a) +``` + +(b) +``` {r 1b} +fit.b <- stan_glm( + y ~ x + z, + data = df, + prior = c(normal(c(0, 0), c(prior.x.sd, 10^3))), + refresh = 0 +) +fit.b +prior_summary(fit.b) +``` + +(c) One appropriate prior for $z$ is the $N(0, 1.5)$. +``` {r 1c} +fit.c <- stan_glm( + y ~ x + z, + data = df, + prior = c(normal(c(0, 0), c(prior.x.sd, 1.5))), + refresh = 0 +) +fit.c +prior_summary(fit.c) +``` + + +## Answer 2 + +The point on the extreme right (on the $x$ scale) has most influence, being the one furthest away from the mean of the $x$ data. + + +## Research homework assignment + + +``` {r rha model1, message = FALSE} +fit.normal <- function(n, M, S) { + y <- rnorm(n, mean = M, sd = S) + stan_glm( + y ~ 1, + prior_intercept = normal(0, 1), + prior_aux = NULL, + refresh = 0 + ) +} +``` + +For $M = 5$, $S = 10$, note that the prior and data will have similar information about $\mu$ when $S^2/n \approx \sigma_{\text{prior}}^2$, i.e. we set $n \approx 100$. + +``` {r rha test1, warning = FALSE} +fit.normal(100, 5, 10) +fit.mu <- replicate(50, coef(fit.normal(100, 5, 10))) +hist(fit.mu, probability = TRUE) +curve(dnorm(x, mean = mean(fit.mu), sd = sd(fit.mu)), add = TRUE) +mean(fit.mu) +sd(fit.mu) +``` + +Note that the fitted values of $\mu$ seem to follow a normal distribution with a mean in the middle of the prior and model means, i.e. between $0$ and $5$. + + +We repeat the same for the second model; we keep the approximation $n = 100$. + +``` {r rha model2, message = FALSE} +fit.t <- function(n, M, S) { + y <- rnorm(n, mean = M, sd = S) + stan_glm( + y ~ 1, + prior_intercept = student_t(df = 1, location = 0, scale = 1), + prior_aux = NULL, + refresh = 0 + ) +} +``` + +``` {r rha test2, warning = FALSE} +fit.t(100, 5, 10) +fit.mu <- replicate(50, coef(fit.t(100, 5, 10))) +hist(fit.mu, probability = TRUE) +``` + +Here, the fitted values of $\mu$ are much more unstable. +This may be explained by the fact that the $t_1(0, 1)$ prior on $\mu$ has fairly heavy tails, making prior draws of $\mu$ erratic. +This, the shrinking effect of the prior on the estimate of $\mu$ seen in the first model is not so apparent in this one. \ No newline at end of file diff --git a/STAT6101/Assignment_5b.pdf b/STAT6101/Assignment_5b.pdf new file mode 100644 index 0000000..2d0804b Binary files /dev/null and b/STAT6101/Assignment_5b.pdf differ diff --git a/STAT6101/Assignment_6a.Rmd b/STAT6101/Assignment_6a.Rmd new file mode 100644 index 0000000..71f6568 --- /dev/null +++ b/STAT6101/Assignment_6a.Rmd @@ -0,0 +1,91 @@ +--- +title: "Assignment 6a" +author: "Satvik Saha" +date: "`r Sys.Date()`" +output: + pdf_document: default +--- + +```{r setup, include=FALSE} +knitr::opts_chunk$set(echo = TRUE) +knitr::opts_chunk$set(fig.pos = "!H", out.extra = "") +``` + +## Answer 1 + +``` {r 1 data, message = FALSE} +library(rstanarm) + +n <- 50 +score_pre <- rnorm(n, mean = 50, sd = 20) +sex <- sample(c(0, 1), n, replace = TRUE) +grade <- sample(c(6, 7, 8), n, replace = TRUE) +score <- 5 + score_pre + 0.0 * sex + ifelse(grade == 7, 5, -5) + 10 * rnorm(n) +df <- data.frame( + score_pre = score_pre, + sex = sex, + grade = grade, + score = score +) +plot(score_pre, score, pch = grade, col = sex + 1) +``` + +(a) With the encoding $0$ for women and $1$ for men, it is easy to read the model without the 'sex' variable as the model for women, and the model without the 'sex' variable but with the coefficient for 'sex' added to the intercept as the model for men. +An encoding with $1$, $2$ for women and men respectively is only slightly more awkward to read off the two models. + +(b) +``` {r 1b} +stan_glm( + score ~ score_pre + sex + grade, + data = df, + refresh = 0 +) +``` + +(c) +``` {r 1c} +stan_glm( + score ~ score_pre + sex + factor(grade), + data = df, + refresh = 0 +) +``` + + +## Answer 2 + +Consider the model $$ + y_i = a + b h_i + c m_i + d h_i m_i + \epsilon_i, +$$ with $\epsilon_i \overset{iid}{\sim} N(0, \sigma^2)$, and $y, h, m$ denoting the variables _earnings, _height_, and _male_. + +We have our estimates $\hat{a} = -9.3, \hat{b} = 0.4, \hat{c} = -29.3, \hat{d} = 0.6$. + +(a) Setting $m_i' = m_i - 0.5$, we may rewrite our model as $$ +\begin{aligned} + y_i &= (a + 0.5 c) + (b + 0.5 d) h_i + c (m_i - 0.5) + d h_i (m_i - 0.5) + \epsilon_i \\ + &= a' + b' h_i + c' m_i' + d' h_i m_i' + \epsilon_i, +\end{aligned} +$$ so our new coefficients are $\hat{a}' = \hat{a} + 0.5 \hat{c} = -23.95$, $\hat{b}' = \hat{b} + 0.5 \hat{d} = 0.7$, $\hat{c}' = \hat{c} = -29.3$, $\hat{d}' = \hat{d} = 0.6$. + +(b) Setting $h_i' = h_i - 66$, we may rewrite our model as $$ +\begin{aligned} + y_i &= (a' + 66b') + b' (h_i - 66) + (c' + 66 d') m_i' + d' (h_i - 66) m_i' + \epsilon_i \\ + &= a'' + b'' h_i + c'' m_i' + d'' h_i' m_i' + \epsilon_i, +\end{aligned} +$$ so our new coefficients are $\hat{a}'' = \hat{a}' + 66\hat{d}' = 15.65$, $\hat{b}'' = \hat{b}' = 0.7$, $\hat{c}'' = \hat{c}' + 66\hat{d}' = 10.3$, $\hat{d}'' = \hat{d}' = 0.6$. + + +(c) Identical to (b) + + + +## Answer 3 + +(a) The estimated regression line for the control group ($z = 0$) can be read as $$ + y = 1.2 + 1.6 x, +$$ and the model for the treatment group ($z = 1$) can be read as $$ + y = 1.2 + 1.6x + 2.7 + 0.7x = 3.9 + 2.3x. +$$ + +(b) +![Control and treatment regression lines](6a3b.pdf){width=450px} \ No newline at end of file diff --git a/STAT6101/Assignment_6a.pdf b/STAT6101/Assignment_6a.pdf new file mode 100644 index 0000000..a1af322 Binary files /dev/null and b/STAT6101/Assignment_6a.pdf differ diff --git a/STAT6101/earnings.csv b/STAT6101/earnings.csv new file mode 100644 index 0000000..077e81a --- /dev/null +++ b/STAT6101/earnings.csv @@ -0,0 +1,1817 @@ +"height","weight","male","earn","earnk","ethnicity","education","mother_education","father_education","walk","exercise","smokenow","tense","angry","age" +74,210,1,50000,50,"White",16,16,16,3,3,2,0,0,45 +66,125,0,60000,60,"White",16,16,16,6,5,1,0,0,58 +64,126,0,30000,30,"White",16,16,16,8,1,2,1,1,29 +65,200,0,25000,25,"White",17,17,NA,8,1,2,0,0,57 +63,110,0,50000,50,"Other",16,16,16,5,6,2,0,0,91 +68,165,0,62000,62,"Black",18,18,18,1,1,2,2,2,54 +63,190,0,51000,51,"White",17,17,17,3,1,2,4,4,39 +64,125,0,9000,9,"White",15,15,15,7,4,1,4,4,26 +62,200,0,29000,29,"White",12,12,12,2,2,2,0,0,49 +73,230,1,32000,32,"White",17,17,17,7,1,1,0,0,46 +72,176,1,2000,2,"Hispanic",15,15,15,8,1,2,0,0,21 +72,265,1,35000,35,"White",NA,99,99,1,1,2,0,0,53 +72,160,1,27000,27,"White",12,12,12,1,2,2,1,1,26 +70,225,1,6530,6.53,"White",16,16,NA,4,1,2,0,0,65 +63,107,0,0,0,"White",14,14,14,7,4,2,2,2,50 +68,170,1,30000,30,"White",11,NA,NA,7,4,2,0,0,34 +68,144,1,12000,12,"White",12,12,12,6,5,2,2,2,27 +71,193,1,15000,15,"White",18,18,18,4,6,2,0,0,51 +65,250,0,12000,12,"White",12,12,12,5,1,2,1,1,51 +66,130,0,20000,20,"White",11,11,11,8,1,1,0,0,45 +60,100,0,0,0,"White",12,12,12,4,2,1,7,7,27 +65,123,0,25000,25,"White",12,12,12,1,4,1,0,0,41 +66,130,0,22000,22,"White",16,16,16,5,1,2,1,1,35 +65,120,0,25000,25,"White",16,16,16,5,4,2,1,1,29 +71,160,1,20000,20,"White",14,14,14,7,4,2,0,0,22 +68,172,1,17000,17,"White",12,12,12,8,1,2,0,0,58 +68,135,0,40000,40,"White",14,14,14,8,7,2,1,1,29 +70,180,1,44000,44,"White",13,13,13,8,2,2,4,4,44 +67,112,0,0,0,"White",9,9,9,1,1,1,0,0,21 +64,240,0,7000,7,"Black",12,12,12,8,1,2,4,4,55 +73,190,1,53000,53,"Black",13,13,13,6,7,2,2,2,35 +64,145,0,5000,5,"Black",12,NA,NA,3,1,1,7,7,23 +62,120,0,5000,5,"White",13,13,13,2,1,1,0,0,51 +63,114,0,14000,14,"White",14,14,14,5,3,2,0,0,21 +69,170,1,45000,45,"White",14,14,14,8,7,2,1,1,36 +67,166,1,5500,5.5,"White",14,14,14,6,7,2,0,0,22 +66,124,0,40000,40,"White",12,12,12,4,4,2,0,0,41 +72,175,1,34000,34,"White",12,12,NA,2,1,2,0,0,45 +63,120,0,5000,5,"Black",12,12,12,4,1,1,7,7,23 +63,184,0,10000,10,"Black",12,12,12,8,3,2,3,3,35 +68,150,1,0,0,"White",11,11,NA,2,7,1,1,1,21 +64,150,0,27000,27,"White",16,16,16,2,1,1,0,0,60 +73,220,1,62000,62,"White",14,14,NA,8,1,2,2,2,44 +67,220,0,15000,15,"White",12,12,12,1,1,2,0,0,69 +60,NA,0,0,0,"White",12,12,12,8,1,2,0,0,44 +72,180,1,50000,50,"White",16,16,16,5,6,2,1,1,38 +68,158,0,0,0,"White",12,NA,NA,3,1,2,0,0,55 +77,255,1,41000,41,"White",16,16,16,7,7,2,0,0,33 +64,150,0,0,0,"White",10,10,10,8,1,2,0,0,19 +64,130,0,15000,15,"White",14,14,14,4,1,2,3,3,25 +64,NA,0,25000,25,"White",12,12,12,1,5,2,7,7,33 +63,146,0,25000,25,"White",16,16,16,5,1,2,1,1,72 +72,185,1,75000,75,"White",17,17,17,8,5,2,4,4,39 +68,180,1,27000,27,"White",17,17,17,5,2,2,0,0,31 +64,135,0,12000,12,"White",12,12,12,8,1,2,7,7,26 +70,168,1,40000,40,"White",12,12,12,7,3,2,0,0,51 +61,138,0,7500,7.5,"White",14,14,14,8,1,1,0,0,78 +65,115,0,25000,25,"White",12,12,12,7,2,1,0,0,46 +67,135,0,30000,30,"Black",14,14,14,8,6,2,7,7,31 +65,150,0,21000,21,"White",12,12,12,8,1,1,0,0,57 +64,120,0,27000,27,"White",14,14,14,5,1,2,0,0,26 +73,165,1,45000,45,"White",16,16,16,7,2,1,0,0,44 +67,130,0,3000,3,"White",15,15,15,1,1,2,1,1,65 +65,170,0,25000,25,"White",12,12,12,8,7,2,2,2,30 +65,140,0,24000,24,"White",12,12,12,1,7,2,1,1,41 +67,145,0,32000,32,"White",18,18,18,4,5,1,1,1,29 +68,145,0,10000,10,"White",17,17,17,7,2,2,1,1,30 +70,150,0,0,0,"White",12,12,12,5,1,2,0,0,57 +60,100,0,11000,11,"Hispanic",12,12,12,2,1,2,0,0,21 +65,105,0,18700,18.7,"White",13,13,13,5,6,2,0,0,32 +62,120,0,20000,20,"White",12,12,12,2,1,1,7,7,29 +72,160,1,3500,3.5,"White",10,10,10,4,7,2,0,0,18 +67,206,1,13000,13,"Black",8,8,8,8,1,2,5,5,56 +70,170,1,25000,25,"White",12,12,12,1,1,2,0,0,65 +70,183,1,21000,21,"White",17,17,17,5,5,2,0,0,41 +68,150,0,34000,34,"White",17,17,17,5,5,2,2,2,49 +66,115,0,5000,5,"Black",12,12,12,7,4,2,1,1,23 +60,120,0,6000,6,"White",12,12,12,1,1,1,0,0,65 +71,195,1,17000,17,"White",12,12,12,8,7,1,1,1,28 +71,140,1,35000,35,"White",12,NA,NA,1,2,1,0,0,32 +73,180,1,4000,4,"White",13,13,13,6,6,2,0,0,18 +64,115,0,5000,5,"White",16,16,16,8,6,2,1,1,22 +68,150,0,14000,14,"White",14,14,14,4,1,2,0,0,55 +66,118,0,10000,10,"White",12,12,12,8,1,2,0,0,57 +69,155,1,25000,25,"White",16,16,16,2,6,2,4,4,29 +63,126,0,0,0,"White",8,NA,8,1,1,1,0,0,63 +70,130,1,87000,87,"White",18,18,18,1,1,2,0,0,60 +63,130,0,16000,16,"White",14,14,14,4,6,2,0,0,27 +66,123,0,0,0,"Black",13,13,13,8,3,2,1,1,30 +66,110,0,15000,15,"White",12,12,12,5,2,2,2,2,33 +64,200,0,0,0,"White",12,NA,NA,4,1,2,3,3,26 +62,130,1,16000,16,"Hispanic",14,14,NA,1,1,2,0,0,28 +66,190,0,25000,25,"White",18,18,18,8,2,2,0,0,67 +64,116,0,16500,16.5,"White",14,14,14,8,7,2,5,5,43 +68,170,1,15000,15,"White",12,12,12,3,7,1,0,0,73 +64,190,0,4000,4,"White",9,9,NA,2,1,2,0,0,68 +67,342,0,3840,3.84,"White",9,9,NA,5,1,2,0,0,52 +60,90,0,5000,5,"White",6,NA,NA,1,1,2,0,0,78 +71,200,1,22000,22,"White",12,12,12,1,6,2,0,0,39 +60,135,0,200,0.2,"White",16,16,16,8,1,2,3,3,53 +66,140,0,26000,26,"White",16,16,16,2,5,2,3,3,27 +66,120,0,2500,2.5,"White",15,15,15,1,1,2,2,2,21 +65,125,0,17000,17,"White",14,14,14,1,1,2,0,0,39 +63,112,0,25000,25,"White",16,16,16,4,5,2,0,0,35 +70,130,0,8000,8,"White",13,13,13,8,7,2,1,1,22 +68,215,1,25000,25,"White",12,NA,12,1,3,2,0,0,31 +65,98,0,0,0,"White",13,13,13,7,1,2,0,0,63 +66,138,0,12000,12,"White",13,13,13,4,1,1,0,0,68 +62,123,0,10000,10,"White",12,12,12,8,6,1,0,0,47 +60,105,0,5000,5,"White",8,8,8,7,1,2,0,0,77 +76,220,1,1e+05,100,"White",16,16,16,3,6,2,0,0,51 +66,140,0,10000,10,"White",15,15,15,8,1,1,2,2,67 +64,173,0,0,0,"White",14,14,14,4,1,1,0,0,38 +72,185,1,15000,15,"White",12,12,12,8,2,2,0,0,39 +66,190,0,45000,45,"Other",12,12,12,8,6,2,0,0,43 +69,190,1,15000,15,"Black",11,NA,NA,4,4,2,0,0,73 +67,115,0,2400,2.4,"Hispanic",8,8,8,8,4,1,1,1,39 +68,150,1,30000,30,"Hispanic",12,12,12,4,6,2,2,2,32 +70,150,1,30000,30,"White",12,12,12,5,6,2,1,1,33 +62,125,0,10000,10,"White",12,12,12,6,4,2,5,5,38 +63,137,0,5000,5,"White",13,13,13,7,2,1,0,0,26 +66,125,0,12000,12,"White",13,13,13,1,1,2,5,5,63 +70,80,0,20000,20,"White",10,10,10,2,1,2,0,0,61 +68,160,0,20000,20,"White",12,12,12,3,1,2,1,1,36 +70,160,1,20000,20,"White",14,14,14,8,7,2,0,0,23 +65,125,0,25000,25,"White",18,18,18,8,7,2,1,1,57 +68,110,0,5000,5,"White",8,NA,NA,1,4,2,0,0,82 +66,133,0,0,0,"White",12,12,12,3,1,2,4,4,59 +71,180,1,25000,25,"White",18,18,18,8,1,2,0,0,76 +66,135,0,1200,1.2,"White",12,12,12,7,7,2,2,2,20 +62,130,0,5000,5,"White",12,12,NA,6,4,2,0,0,69 +68,120,0,700,0.7,"White",16,16,16,4,5,2,0,0,32 +70,150,1,20000,20,"White",16,16,16,1,4,1,0,0,27 +61,110,0,10000,10,"Hispanic",12,12,12,8,6,1,0,0,22 +63,128,0,30000,30,"White",12,12,12,7,7,2,0,0,73 +72,185,1,25000,25,"Hispanic",8,NA,NA,8,1,2,0,0,63 +64,200,0,40000,40,"White",14,14,NA,8,7,2,0,0,56 +67,155,1,25000,25,"White",12,NA,NA,8,7,2,0,0,89 +66,135,0,45000,45,"White",18,18,18,5,2,2,0,0,65 +61,130,0,10000,10,"White",17,17,17,7,1,2,0,0,79 +69,132,0,60000,60,"White",18,18,18,8,1,2,0,0,63 +62,103,0,45000,45,"White",12,12,12,8,1,2,0,0,56 +64,150,0,0,0,"White",12,NA,NA,4,7,2,3,3,21 +68,130,0,18000,18,"White",12,12,12,7,1,1,0,0,66 +60,128,0,15000,15,"White",12,NA,NA,4,5,2,5,5,74 +71,155,1,50000,50,"White",18,18,18,8,3,2,1,1,42 +64,155,0,16040,16.04,"White",12,NA,NA,8,1,2,3,3,33 +67,140,0,15000,15,"Black",14,14,14,8,1,1,7,7,30 +69,160,1,10000,10,"White",17,17,NA,1,7,2,2,2,23 +67,185,0,33000,33,"White",13,13,13,2,1,2,0,0,43 +68,130,0,18000,18,"White",12,12,12,7,7,2,0,0,30 +63,105,0,15000,15,"White",12,12,12,7,1,2,7,7,37 +71,145,1,21000,21,"White",12,NA,12,4,7,2,0,0,22 +64,124,0,21000,21,"Black",17,17,17,3,1,2,0,0,43 +68,170,1,37000,37,"White",11,11,11,4,4,2,2,2,37 +68,126,0,38000,38,"White",17,17,17,7,6,2,2,2,44 +66,142,0,17000,17,"Hispanic",14,14,14,4,4,1,0,0,43 +66,130,0,0,0,"White",12,12,12,4,3,1,2,2,29 +66,130,0,0,0,"Other",16,16,16,8,2,2,0,0,32 +60,100,0,15000,15,"White",16,16,16,1,1,2,1,1,91 +77,210,1,32000,32,"White",16,16,16,1,7,2,1,1,30 +67,160,0,27500,27.5,"White",12,12,12,4,1,2,0,0,58 +66,140,1,15000,15,"White",12,NA,NA,8,1,1,0,0,76 +62,120,0,16500,16.5,"White",12,12,12,8,1,1,3,3,44 +64,118,0,0,0,"White",17,17,17,8,6,2,5,5,30 +72,175,0,0,0,"White",12,12,12,7,1,2,2,2,51 +67,150,0,25000,25,"White",18,18,18,7,5,2,1,1,35 +61,116,0,27000,27,"White",18,18,18,4,7,2,2,2,43 +64,220,0,5000,5,"White",12,NA,12,5,1,1,7,7,28 +62,125,0,70000,70,"White",16,16,16,8,1,2,0,0,38 +63,150,0,5000,5,"White",12,12,12,4,5,2,2,2,40 +68,135,1,5000,5,"White",16,16,16,1,4,2,1,1,24 +69,158,1,62000,62,"Other",18,18,18,4,1,2,1,1,30 +64,160,0,15000,15,"Black",12,12,12,8,1,1,0,0,59 +64,158,0,20000,20,"White",15,15,15,8,4,1,0,0,26 +72,185,1,4000,4,"White",15,15,15,4,5,1,2,2,21 +72,172,1,75000,75,"White",12,12,12,7,6,2,0,0,39 +64,130,0,60000,60,"White",16,16,16,5,1,2,2,2,35 +61,150,0,5000,5,"White",13,13,13,8,1,2,7,7,31 +74,230,1,30000,30,"White",12,12,12,7,4,1,3,3,38 +70,165,1,70000,70,"White",14,14,14,5,4,1,2,2,35 +64,115,0,5000,5,"White",16,16,16,8,1,2,0,0,60 +71,195,1,50000,50,"White",16,16,16,8,4,1,0,0,41 +63,120,0,44000,44,"White",12,12,12,8,6,1,0,0,39 +73,215,1,40000,40,"White",18,18,18,4,4,1,0,0,40 +64,133,0,30000,30,"White",14,14,14,4,7,2,2,2,43 +73,200,1,15000,15,"Black",14,14,NA,8,7,2,2,2,24 +63,150,0,35000,35,"White",15,15,15,6,1,2,0,0,31 +62,130,0,0,0,"White",16,16,16,5,1,2,6,6,32 +62,140,0,10000,10,"White",16,16,16,3,1,2,7,7,40 +70,170,0,23000,23,"White",17,17,17,6,3,2,5,5,42 +62,115,0,0,0,"White",12,12,12,1,1,2,7,7,39 +71,175,1,45000,45,"White",17,17,17,6,1,2,0,0,62 +71,170,1,15000,15,"White",14,14,14,8,6,1,0,0,31 +70,169,0,4000,4,"White",14,14,14,8,1,2,0,0,71 +67,160,1,17000,17,"White",14,14,14,1,6,2,0,0,31 +64,130,0,30000,30,"White",12,12,12,6,4,2,3,3,32 +67,112,0,27500,27.5,"White",12,12,12,3,3,1,1,1,30 +62,140,0,5688,5.688,"White",8,8,NA,6,1,2,3,3,69 +62,137,0,18000,18,"Hispanic",13,13,13,6,1,2,0,0,56 +67,170,1,35000,35,"White",14,14,14,6,7,2,3,3,36 +66,160,0,45000,45,"White",17,17,17,8,1,2,0,0,32 +68,185,1,43000,43,"Black",13,13,13,7,1,2,7,7,44 +62,140,0,32000,32,"Black",14,14,14,6,2,2,1,1,44 +62,118,0,25000,25,"Black",12,12,NA,7,7,2,0,0,20 +66,148,0,0,0,"Black",5,5,NA,6,1,2,1,1,51 +68,165,0,10000,10,"Black",18,18,18,3,2,2,4,4,56 +65,130,0,50000,50,"Hispanic",12,12,12,8,1,2,1,1,38 +74,160,1,15000,15,"White",12,12,12,2,5,1,3,3,20 +74,185,1,60000,60,"White",13,13,13,8,3,1,0,0,45 +71,175,1,30000,30,"White",15,15,15,1,1,2,0,0,23 +68,150,0,21000,21,"Other",12,12,12,8,4,2,5,5,50 +62,110,0,2400,2.4,"White",16,16,16,3,4,2,7,7,22 +68,240,0,5000,5,"White",10,10,10,8,7,1,0,0,50 +62,150,0,35000,35,"Black",15,15,15,2,1,2,2,2,42 +66,136,0,1000,1,"White",15,15,15,5,7,2,0,0,28 +68,170,1,27000,27,"White",12,12,12,8,1,1,3,3,27 +60,115,0,6600,6.6,"Hispanic",14,14,14,8,6,1,2,2,28 +68,164,1,16000,16,"White",8,8,8,4,1,2,2,2,43 +72,185,1,90000,90,"White",12,12,12,8,7,2,6,6,26 +66,185,0,8000,8,"White",12,12,NA,5,2,1,0,0,42 +68,150,1,20000,20,"White",10,NA,NA,1,1,2,0,0,32 +68,130,0,15000,15,"White",12,12,12,6,7,1,5,5,18 +69,180,0,12000,12,"White",12,12,12,8,1,2,0,0,60 +63,170,0,25000,25,"White",9,9,NA,8,2,2,2,2,67 +64,128,0,24000,24,"White",16,16,16,7,3,2,0,0,46 +65,175,0,20000,20,"White",14,14,14,8,3,2,0,0,39 +61,128,0,19000,19,"White",12,12,12,8,1,2,0,0,46 +71,180,1,25000,25,"White",8,NA,8,3,1,1,0,0,53 +72,172,1,10000,10,"White",12,12,12,8,1,2,0,0,49 +66,125,0,40000,40,"White",16,16,16,8,1,1,1,1,34 +69,175,1,62000,62,"Black",8,NA,NA,1,1,2,0,0,35 +63,105,0,25000,25,"Black",13,13,13,7,6,2,3,3,38 +62,NA,0,0,0,"White",10,10,NA,8,1,1,6,6,57 +60,145,0,0,0,"Hispanic",10,10,NA,8,1,2,0,0,48 +62,138,0,10000,10,"White",8,NA,NA,2,1,2,0,0,88 +68,160,1,25000,25,"White",14,14,14,8,1,2,0,0,64 +70,150,1,25000,25,"White",12,12,NA,4,6,2,0,0,24 +71,165,1,25000,25,"White",14,14,14,4,5,1,0,0,32 +71,209,1,19000,19,"White",16,16,16,8,4,2,4,4,61 +68,210,1,44000,44,"White",16,16,16,4,4,2,2,2,48 +66,145,0,0,0,"White",12,12,12,8,6,2,0,0,19 +63,140,0,0,0,"White",18,18,18,8,1,1,0,0,55 +60,105,0,15000,15,"White",14,14,14,8,2,1,0,0,49 +63,137,0,17000,17,"White",12,12,NA,5,1,2,5,5,36 +68,150,1,24000,24,"White",12,12,12,1,1,2,0,0,56 +70,150,1,50000,50,"White",16,16,16,8,6,2,0,0,38 +64,170,0,23000,23,"White",12,12,12,8,1,2,7,7,37 +70,143,1,13000,13,"White",12,12,12,8,7,2,0,0,74 +66,178,0,20000,20,"Black",NA,NA,NA,8,1,2,0,0,72 +66,NA,0,45000,45,"White",12,12,12,4,7,1,7,7,49 +68,180,1,65000,65,"White",16,16,16,1,6,2,1,1,46 +61,135,0,7000,7,"White",12,12,NA,4,1,2,3,3,63 +68,180,1,40000,40,"White",18,18,18,8,2,2,0,0,63 +66,145,0,15000,15,"White",17,17,17,7,1,2,3,3,43 +70,164,1,20000,20,"White",16,16,16,5,5,2,0,0,25 +68,150,1,25000,25,"White",6,NA,NA,1,1,1,0,0,77 +71,175,1,20000,20,"White",12,12,12,8,2,2,7,7,50 +63,175,1,5000,5,"White",9,NA,9,2,1,2,0,0,67 +65,195,0,20000,20,"White",12,12,12,8,1,2,0,0,42 +66,150,0,25000,25,"White",12,12,12,3,1,2,0,0,49 +64,110,0,15000,15,"White",14,14,14,8,6,2,0,0,20 +70,195,1,49000,49,"White",13,13,13,7,7,1,0,0,37 +70,165,1,25000,25,"White",8,8,8,8,7,1,0,0,24 +64,102,0,0,0,"White",12,NA,12,3,1,2,3,3,36 +63,150,0,0,0,"White",16,16,16,6,4,2,7,7,35 +62,158,0,25000,25,"White",12,12,12,5,1,2,0,0,65 +65,160,0,30000,30,"White",12,12,12,5,1,2,0,0,67 +66,142,0,25000,25,"White",12,12,12,8,1,2,1,1,62 +60,125,0,35000,35,"White",16,16,16,8,1,2,0,0,72 +66,128,0,11000,11,"White",14,14,14,7,1,2,0,0,57 +61,160,0,16000,16,"White",15,15,15,3,7,2,1,1,38 +72,145,1,35000,35,"White",14,14,14,1,7,2,2,2,43 +74,240,1,125000,125,"White",18,18,18,4,1,2,7,7,45 +67,185,0,23000,23,"White",12,12,12,3,1,1,2,2,47 +66,170,0,17000,17,"White",16,16,16,1,1,2,1,1,28 +62,125,0,0,0,"White",13,13,13,2,2,1,7,7,31 +62,115,0,27000,27,"White",12,12,12,2,1,2,3,3,41 +72,180,1,70000,70,"White",14,14,14,8,7,2,0,0,32 +65,170,0,35000,35,"White",15,15,15,8,1,2,0,0,47 +60,150,0,10000,10,"White",12,12,12,1,1,1,3,3,62 +64,107,0,15000,15,"White",13,NA,13,8,4,1,4,4,30 +62,135,0,35000,35,"White",15,15,15,6,6,2,0,0,39 +66,130,0,15000,15,"White",12,12,12,8,5,2,1,1,38 +64,250,0,12000,12,"White",12,12,12,7,6,2,0,0,39 +71,135,1,8000,8,"White",12,NA,NA,1,1,1,0,0,68 +65,130,0,8000,8,"White",12,12,12,7,1,1,0,0,50 +73,225,1,35000,35,"White",18,18,18,5,2,2,0,0,50 +69,175,1,45000,45,"White",11,NA,NA,8,1,1,0,0,51 +64,175,0,0,0,"White",12,12,12,8,7,2,0,0,58 +64,118,0,5000,5,"White",12,12,12,7,7,2,4,4,27 +64,123,0,15000,15,"White",14,14,14,4,2,2,0,0,22 +61,136,0,15000,15,"White",12,12,12,6,1,2,3,3,77 +67,240,0,24000,24,"White",18,18,18,7,2,2,3,3,51 +62,189,0,25000,25,"White",13,13,13,5,1,1,5,5,32 +63,165,0,25000,25,"Black",14,14,14,4,2,2,0,0,54 +67,105,1,20000,20,"Other",10,10,NA,1,1,1,0,0,28 +68,140,0,24000,24,"White",12,12,12,8,4,2,0,0,24 +72,165,1,44000,44,"White",16,16,16,8,4,2,1,1,46 +70,187,1,69000,69,"White",12,12,12,7,1,1,0,0,38 +70,188,1,62000,62,"White",18,18,18,8,4,2,0,0,44 +60,145,0,25000,25,"Black",15,15,15,2,1,2,1,1,65 +67,170,1,32000,32,"Black",14,14,14,6,6,2,0,0,32 +63,125,0,20000,20,"Black",12,12,12,8,1,1,0,0,33 +66,112,0,32000,32,"Other",18,18,18,5,2,2,0,0,35 +66,135,0,25000,25,"White",17,17,17,8,5,2,1,1,50 +71,185,1,170000,170,"White",18,18,18,5,4,2,0,0,45 +66,185,0,0,0,"Black",11,11,11,8,5,2,2,2,29 +67,170,1,35000,35,"White",16,16,16,1,7,2,0,0,33 +76,194,1,40000,40,"Black",16,16,16,5,6,2,1,1,38 +69,155,1,33000,33,"White",14,14,14,5,7,2,3,3,30 +65,145,0,18000,18,"White",12,12,12,2,3,2,0,0,22 +62,120,0,30000,30,"White",13,13,13,2,1,1,1,1,43 +62,112,0,26000,26,"White",12,12,12,2,1,1,7,7,31 +62,120,0,5000,5,"White",12,12,12,2,2,1,4,4,21 +69,163,0,5000,5,"White",12,12,12,2,1,1,7,7,18 +62,130,0,20000,20,"White",16,16,16,8,1,2,0,0,73 +61,105,0,17000,17,"White",12,12,12,5,6,1,0,0,30 +65,138,0,32000,32,"White",14,14,14,2,1,1,2,2,28 +72,170,1,15000,15,"White",14,14,14,7,6,2,0,0,22 +66,120,0,0,0,"White",17,17,17,8,6,2,3,3,41 +72,248,1,50000,50,"White",14,14,14,8,1,2,0,0,55 +64,138,0,8000,8,"White",12,NA,NA,3,2,2,2,2,39 +71,190,1,40000,40,"White",14,14,14,8,3,2,0,0,51 +72,185,1,40000,40,"White",15,15,15,8,6,2,3,3,41 +66,130,1,32750,32.75,"White",12,12,NA,7,5,1,0,0,34 +68,170,1,5000,5,"White",12,12,12,8,3,1,5,5,20 +65,185,0,20000,20,"White",14,14,14,3,1,2,0,0,69 +65,128,0,36000,36,"Black",15,15,15,8,7,2,0,0,39 +62,170,0,6000,6,"White",12,NA,NA,3,7,2,0,0,64 +66,160,0,12000,12,"Hispanic",14,14,14,7,7,2,2,2,34 +67,150,1,60000,60,"White",14,14,14,8,7,2,0,0,63 +64,135,0,40000,40,"White",13,13,13,8,2,1,0,0,44 +74,185,1,5000,5,"Hispanic",13,13,13,5,7,2,0,0,19 +63,117,0,43000,43,"White",12,12,12,5,6,2,0,0,38 +67,150,0,45000,45,"White",16,16,16,8,1,2,3,3,34 +68,190,0,6000,6,"White",18,18,18,3,1,2,5,5,39 +64,154,0,8000,8,"Other",10,NA,10,7,1,2,0,0,82 +64,170,0,20000,20,"Black",13,13,13,8,1,2,5,5,39 +66,165,1,17000,17,"Black",12,12,12,8,6,2,0,0,23 +65,112,0,2000,2,"White",12,NA,NA,6,1,1,7,7,32 +65,180,1,65000,65,"White",12,12,12,8,3,2,0,0,28 +72,180,1,50000,50,"White",12,12,12,4,4,2,1,1,41 +68,128,0,0,0,"White",11,11,11,6,5,1,1,1,54 +63,170,0,0,0,"White",11,11,11,5,3,2,0,0,29 +70,220,1,15000,15,"White",13,NA,NA,1,1,2,0,0,21 +68,140,0,11000,11,"White",12,12,12,8,1,2,1,1,38 +74,190,1,35000,35,"White",18,18,18,5,7,2,0,0,30 +63,185,1,27000,27,"White",12,12,12,1,2,2,1,1,33 +64,135,0,3500,3.5,"White",12,12,12,8,1,2,0,0,61 +65,132,0,15000,15,"White",7,7,7,1,1,1,0,0,77 +68,180,1,42000,42,"White",12,12,12,8,4,1,2,2,37 +61,200,0,15000,15,"White",12,12,NA,5,1,2,0,0,61 +67,130,0,20000,20,"White",18,18,18,3,3,2,0,0,29 +67,125,0,15000,15,"White",12,12,12,8,1,1,3,3,29 +73,207,1,10000,10,"White",12,12,12,2,7,2,1,1,21 +62,105,0,0,0,"White",12,NA,NA,1,1,1,2,2,48 +70,176,1,6000,6,"White",8,8,8,8,7,2,0,0,78 +71,200,1,25000,25,"White",12,NA,NA,5,1,2,2,2,80 +65,200,0,17000,17,"Hispanic",16,NA,NA,8,1,2,3,3,23 +69,148,1,35000,35,"Hispanic",16,16,16,8,1,2,0,0,65 +77,203,1,28000,28,"White",14,14,14,8,7,2,0,0,28 +68,165,0,15000,15,"White",12,NA,NA,6,3,1,1,1,33 +62,110,0,20000,20,"White",17,17,17,6,1,1,0,0,24 +64,128,0,20000,20,"White",12,12,12,4,1,2,3,3,29 +67,150,1,10500,10.5,"Hispanic",12,12,NA,7,4,2,1,1,42 +70,165,1,13000,13,"White",16,16,16,7,7,2,2,2,22 +62,123,0,10000,10,"White",12,12,12,1,4,2,7,7,52 +63,170,0,3000,3,"White",12,12,NA,8,3,2,5,5,37 +62,116,0,24000,24,"White",14,14,14,1,4,1,7,7,29 +63,117,0,0,0,"White",17,17,17,1,1,2,4,4,41 +69,160,0,17000,17,"White",13,13,13,1,1,1,7,7,35 +64,122,0,11000,11,"White",12,12,NA,1,1,1,0,0,48 +64,154,0,0,0,"White",14,14,14,6,1,2,7,7,37 +69,185,0,32000,32,"White",14,14,14,1,4,1,4,4,40 +59,95,0,17000,17,"White",15,15,15,2,1,2,5,5,26 +61,115,0,15000,15,"White",16,16,16,5,6,2,0,0,47 +60,125,0,25000,25,"White",12,12,12,4,1,2,0,0,75 +72,225,1,136500,136.5,"White",12,12,12,4,4,2,0,0,49 +66,NA,0,3000,3,"Other",12,12,NA,7,7,2,7,7,35 +63,160,0,15000,15,"White",8,NA,NA,8,6,2,0,0,60 +65,150,0,0,0,"White",12,12,12,1,1,1,0,0,41 +70,200,1,25000,25,"White",18,18,18,8,1,2,1,1,58 +72,250,1,5000,5,"White",14,14,14,2,1,2,0,0,48 +62,125,0,2100,2.1,"Black",12,12,12,6,1,1,6,6,21 +70,148,1,15000,15,"Black",10,10,10,8,1,1,0,0,82 +60,120,0,15000,15,"White",13,NA,13,8,1,2,0,0,76 +66,140,0,15000,15,"Black",12,12,12,2,1,2,3,3,29 +64,160,1,15000,15,"Hispanic",12,12,12,8,6,1,0,0,34 +71,180,1,15000,15,"White",16,16,16,2,6,2,2,2,23 +73,250,1,5000,5,"Black",12,12,12,7,5,1,0,0,27 +75,180,1,3192,3.192,"Black",11,11,11,8,7,1,0,0,34 +62,110,0,15000,15,"Other",12,12,12,6,1,2,0,0,25 +63,123,0,17000,17,"White",17,17,17,5,5,2,1,1,26 +65,150,0,30000,30,"White",13,13,13,7,7,2,7,7,28 +70,135,1,15000,15,"White",12,12,12,1,1,2,0,0,32 +64,110,0,5000,5,"White",16,16,16,7,6,2,0,0,26 +68,170,0,24000,24,"White",16,16,16,6,4,2,1,1,42 +65,154,0,10000,10,"White",14,14,14,8,1,2,0,0,67 +69,150,1,50000,50,"White",8,8,8,2,7,1,0,0,53 +64,170,0,15000,15,"White",11,NA,NA,1,1,2,0,0,77 +72,168,1,50000,50,"White",16,16,16,3,2,2,0,0,53 +69,160,1,136500,136.5,"White",12,12,12,8,2,1,0,0,38 +64,150,0,20000,20,"White",17,17,17,4,2,2,0,0,49 +63,108,0,30000,30,"Hispanic",18,18,18,7,2,2,0,0,54 +68,122,0,5000,5,"White",18,18,18,2,1,2,2,2,41 +64,135,0,0,0,"White",12,12,12,1,1,1,1,1,63 +66,130,0,0,0,"White",10,10,10,6,1,2,0,0,48 +70,165,1,25000,25,"White",12,12,12,1,1,2,0,0,37 +63,134,0,0,0,"White",5,NA,5,7,1,2,0,0,58 +73,180,0,22000,22,"White",14,14,14,5,1,2,0,0,45 +75,200,1,27000,27,"White",12,12,12,1,7,2,0,0,24 +65,210,0,4000,4,"White",12,12,12,4,2,2,1,1,38 +64,140,0,35000,35,"White",16,16,16,8,4,2,0,0,41 +66,160,0,17500,17.5,"White",17,17,17,4,1,2,0,0,26 +66,112,0,16500,16.5,"White",14,14,14,7,6,2,3,3,28 +64,190,0,28000,28,"White",16,16,16,3,1,2,5,5,39 +66,140,0,52000,52,"White",18,18,18,2,5,2,0,0,50 +64,108,0,15000,15,"White",16,16,16,2,6,2,0,0,29 +63,140,0,19000,19,"White",13,13,13,8,7,2,2,2,32 +63,125,0,0,0,"White",13,13,13,8,4,2,0,0,44 +67,132,0,5000,5,"Black",12,12,NA,3,1,2,2,2,19 +69,135,0,15000,15,"White",12,12,NA,5,1,2,1,1,34 +73,170,1,27000,27,"White",12,12,12,6,6,1,2,2,23 +72,171,1,15000,15,"White",8,8,8,1,7,1,6,6,58 +66,196,0,0,0,"White",12,12,12,1,2,2,5,5,24 +72,195,1,15000,15,"White",14,14,14,8,5,2,1,1,33 +64,150,0,14500,14.5,"White",12,NA,NA,7,1,2,0,0,55 +64,106,0,24000,24,"White",13,13,13,2,1,2,0,0,30 +61,115,0,5000,5,"White",12,12,12,4,2,2,1,1,18 +68,145,1,18000,18,"White",15,15,15,7,7,2,0,0,36 +62,118,0,4000,4,"White",12,12,12,8,2,2,0,0,68 +64,129,0,15000,15,"White",12,NA,NA,6,1,2,0,0,85 +69,NA,0,4000,4,"White",13,13,13,6,1,2,0,0,57 +66,160,0,20000,20,"White",15,15,15,4,7,2,0,0,53 +60,98,0,700,0.7,"White",12,12,12,8,1,2,7,7,36 +64,123,0,25000,25,"White",15,15,NA,7,7,2,0,0,33 +65,220,0,24000,24,"White",12,12,12,4,1,2,2,2,91 +60,125,0,15000,15,"White",12,NA,NA,2,1,2,0,0,60 +76,215,1,27000,27,"White",12,12,12,7,7,2,0,0,39 +72,NA,0,12000,12,"White",12,12,12,7,7,2,5,5,35 +72,185,1,4e+05,400,"White",12,12,12,5,4,2,6,6,33 +62,145,0,22000,22,"White",18,18,18,4,7,2,2,2,47 +62,140,0,30000,30,"White",13,13,13,1,1,2,1,1,36 +70,160,1,45000,45,"White",16,16,16,7,6,2,0,0,35 +71,205,1,35000,35,"White",12,12,12,8,3,2,0,0,61 +74,195,1,20000,20,"White",12,12,12,8,2,2,7,7,42 +65,138,0,32000,32,"White",16,16,16,5,1,2,0,0,32 +63,160,0,6000,6,"Other",12,12,12,4,1,1,2,2,31 +67,150,0,12000,12,"White",12,12,12,3,1,1,0,0,39 +65,128,0,0,0,"White",16,16,16,2,1,1,0,0,44 +63,145,0,10000,10,"White",12,12,12,3,1,2,1,1,31 +65,126,0,1000,1,"White",12,12,NA,6,6,1,0,0,18 +64,136,0,12000,12,"White",15,NA,NA,7,6,1,0,0,71 +65,140,0,16000,16,"White",12,12,12,7,1,2,1,1,36 +63,125,0,15000,15,"White",13,13,13,7,1,2,2,2,27 +68,240,0,0,0,"White",16,16,16,8,1,2,5,5,41 +63,140,0,25000,25,"White",16,16,16,4,2,2,0,0,33 +70,135,0,25000,25,"White",12,12,NA,5,7,2,2,2,27 +68,180,1,32000,32,"White",12,12,NA,5,6,2,5,5,30 +67,165,1,35000,35,"White",14,14,14,1,5,2,0,0,43 +68,130,1,25000,25,"White",12,12,12,8,2,1,7,7,24 +66,135,0,25000,25,"White",12,12,12,3,1,2,2,2,23 +65,125,0,6000,6,"White",12,12,12,8,1,1,1,1,28 +69,165,1,80000,80,"White",14,14,14,4,3,1,0,0,44 +68,145,0,20000,20,"White",14,14,14,7,1,2,0,0,25 +66,187,0,1000,1,"White",17,17,17,2,1,2,0,0,38 +71,165,1,28000,28,"Hispanic",13,13,13,1,5,1,0,0,38 +64,125,1,26000,26,"Hispanic",16,16,16,7,7,2,0,0,23 +74,210,1,27000,27,"White",12,12,12,7,6,2,2,2,24 +62,112,0,18000,18,"White",13,13,13,5,3,2,2,2,41 +65,200,0,2000,2,"White",12,12,12,8,1,2,0,0,59 +69,195,1,20000,20,"White",12,12,12,4,5,2,0,0,66 +72,185,1,15000,15,"Black",12,12,12,8,2,2,2,2,19 +66,221,0,6000,6,"White",16,16,16,4,1,2,1,1,48 +70,180,1,15000,15,"White",11,11,11,8,4,2,0,0,32 +61,170,0,15000,15,"White",12,NA,NA,1,3,2,0,0,74 +60,110,0,0,0,"White",10,10,10,1,1,2,0,0,68 +70,190,1,5000,5,"White",12,12,12,2,4,2,2,2,19 +73,130,0,5000,5,"White",11,11,11,8,7,1,0,0,21 +66,160,0,15000,15,"White",12,12,12,7,1,2,1,1,74 +57,130,0,45000,45,"Hispanic",12,12,12,2,1,2,0,0,36 +67,210,1,25000,25,"White",11,11,11,8,7,2,0,0,63 +73,180,1,12000,12,"White",12,NA,NA,8,3,2,0,0,29 +65,115,0,0,0,"White",18,18,18,4,5,2,3,3,26 +62,120,0,15000,15,"White",12,12,12,6,1,2,0,0,45 +76,165,1,12000,12,"White",12,12,NA,8,1,1,0,0,57 +70,175,1,30000,30,"White",14,14,14,8,5,2,0,0,76 +64,160,0,0,0,"White",12,12,12,6,6,2,2,2,30 +63,130,0,4000,4,"Black",15,15,15,4,4,2,4,4,22 +67,185,0,5000,5,"Black",11,11,11,8,1,2,2,2,18 +63,115,0,26000,26,"Black",13,13,13,7,7,2,0,0,37 +69,190,0,5000,5,"White",9,9,NA,8,4,2,0,0,53 +67,200,0,15000,15,"White",9,9,9,1,1,1,7,7,23 +66,180,0,15000,15,"Black",12,12,12,4,4,1,7,7,30 +61,140,0,5000,5,"Black",12,12,12,7,7,2,1,1,25 +70,164,1,23000,23,"Black",12,12,12,8,7,1,4,4,35 +71,175,1,21000,21,"White",12,12,12,8,1,1,7,7,33 +65,135,0,25000,25,"White",12,12,12,5,1,2,3,3,62 +70,157,1,18000,18,"White",16,NA,16,4,1,2,1,1,75 +63,150,0,4000,4,"White",13,13,13,4,6,2,0,0,44 +64,116,0,23900,23.9,"White",12,12,12,8,7,2,2,2,22 +68,145,1,35000,35,"White",12,NA,NA,8,5,2,0,0,68 +64,123,0,35000,35,"White",18,18,18,3,6,2,1,1,40 +67,140,1,26000,26,"White",14,14,14,1,4,1,3,3,30 +66,172,1,25000,25,"White",16,16,16,2,2,2,1,1,36 +68,118,0,23500,23.5,"White",13,13,13,2,4,1,7,7,27 +65,135,0,12000,12,"White",12,12,12,1,1,2,1,1,22 +67,140,0,15000,15,"White",12,12,12,5,6,2,2,2,20 +61,165,0,25000,25,"White",8,NA,NA,7,1,2,0,0,67 +73,210,1,3000,3,"White",17,17,17,5,6,2,0,0,23 +63,200,0,15000,15,"White",12,12,12,2,1,2,0,0,68 +66,145,0,20000,20,"White",12,12,12,1,7,2,0,0,37 +64,200,0,6000,6,"White",12,12,12,8,1,2,2,2,67 +71,160,1,14000,14,"White",12,12,12,1,1,2,0,0,69 +63,123,0,15000,15,"White",16,16,16,3,1,2,2,2,31 +71,180,1,175000,175,"White",16,16,16,8,5,2,2,2,48 +63,118,0,0,0,"White",12,12,12,3,1,1,1,1,51 +64,128,0,62000,62,"White",16,16,16,5,1,2,1,1,70 +73,170,1,1000,1,"White",18,18,18,7,7,2,3,3,25 +65,140,0,10000,10,"White",14,14,14,6,2,2,0,0,63 +66,120,1,45000,45,"White",13,NA,13,4,1,2,0,0,82 +66,120,0,15000,15,"White",12,NA,NA,1,1,1,0,0,81 +60,135,0,45000,45,"White",15,15,15,8,1,2,0,0,79 +68,165,0,50000,50,"White",18,18,18,4,1,1,2,2,52 +59,140,0,20000,20,"White",13,13,NA,8,1,2,4,4,41 +70,215,1,5000,5,"White",12,12,12,2,6,1,2,2,42 +70,165,1,35000,35,"White",16,16,16,1,7,2,2,2,30 +72,152,1,40000,40,"White",16,16,16,4,7,2,0,0,28 +64,135,0,35000,35,"White",12,12,12,8,7,2,0,0,72 +72,200,1,25000,25,"White",12,12,12,8,2,1,1,1,33 +66,170,0,50000,50,"White",16,16,16,4,4,2,0,0,54 +70,205,1,1e+05,100,"White",18,18,18,5,1,1,0,0,57 +69,145,1,35000,35,"White",13,NA,NA,1,7,1,0,0,28 +66,115,0,0,0,"White",12,12,12,5,5,2,2,2,51 +68,175,0,24000,24,"White",12,12,12,3,1,1,0,0,35 +64,120,0,0,0,"White",12,12,12,4,1,1,4,4,30 +67,140,0,25000,25,"White",14,14,14,8,1,2,2,2,35 +63,124,0,0,0,"White",12,12,NA,2,1,2,0,0,60 +74,268,1,35000,35,"White",17,17,17,6,1,1,0,0,43 +73,230,1,38000,38,"White",16,NA,NA,7,5,2,0,0,74 +70,200,1,35000,35,"White",13,13,13,8,4,1,0,0,29 +60,130,0,25000,25,"White",8,8,8,8,1,2,0,0,76 +67,160,1,30000,30,"White",12,12,12,8,6,2,0,0,52 +64,136,0,5000,5,"Hispanic",12,12,NA,5,1,2,2,2,39 +67,160,1,148000,148,"White",18,18,18,1,4,2,0,0,38 +70,165,1,30000,30,"White",12,12,12,2,1,2,0,0,32 +64,120,0,6500,6.5,"White",15,15,15,8,6,2,1,1,31 +62,95,0,3000,3,"White",16,16,16,8,2,2,7,7,37 +72,175,1,25000,25,"White",15,15,NA,8,1,1,0,0,75 +66,200,0,0,0,"White",8,NA,8,1,1,1,2,2,53 +69,230,1,23000,23,"White",18,18,18,3,6,2,0,0,69 +82,175,1,45000,45,"White",18,NA,18,4,1,2,1,1,65 +63,150,0,35000,35,"White",16,16,16,8,1,2,0,0,36 +68,155,1,40000,40,"White",17,17,17,8,6,2,2,2,41 +72,180,1,30000,30,"White",14,14,14,8,2,2,1,1,39 +63,210,0,0,0,"White",14,14,14,8,2,1,7,7,29 +63,210,0,14000,14,"White",12,12,NA,6,5,1,0,0,37 +69,NA,0,15000,15,"White",12,12,12,8,1,2,7,7,34 +64,120,0,26000,26,"White",18,18,18,4,2,1,0,0,36 +71,195,0,8000,8,"White",12,12,12,8,7,1,7,7,25 +64,123,0,24000,24,"Black",16,16,16,8,6,1,4,4,27 +72,135,1,0,0,"White",8,8,8,5,5,1,0,0,20 +62,125,0,0,0,"White",12,12,12,8,2,1,7,7,25 +66,180,0,0,0,"White",10,10,10,8,5,2,3,3,38 +72,200,1,15000,15,"White",12,NA,NA,1,1,2,0,0,40 +66,140,1,5124,5.124,"White",8,8,8,1,1,1,3,3,67 +61,110,0,10000,10,"White",15,15,15,2,4,2,3,3,25 +64,165,0,5000,5,"White",7,NA,NA,5,1,1,1,1,38 +62,111,0,5000,5,"Black",13,13,13,8,5,2,0,0,20 +69,125,0,0,0,"White",13,13,NA,8,7,2,1,1,19 +68,145,0,12000,12,"White",16,16,16,7,1,2,7,7,32 +66,155,0,0,0,"White",12,12,12,5,7,1,7,7,23 +68,180,1,50000,50,"White",17,17,17,7,6,2,0,0,34 +71,158,1,136500,136.5,"White",16,16,16,5,5,1,0,0,41 +64,125,0,23000,23,"White",13,13,13,4,2,2,1,1,26 +61,118,0,0,0,"White",16,16,16,7,1,2,1,1,40 +68,155,0,25000,25,"White",12,12,12,4,1,2,0,0,69 +63,174,0,5000,5,"White",9,NA,NA,5,1,2,0,0,69 +65,138,0,5000,5,"White",12,NA,NA,8,1,2,1,1,91 +64,110,0,5000,5,"White",12,12,12,8,1,2,5,5,18 +65,130,0,15000,15,"White",12,12,12,8,7,1,0,0,38 +64,125,0,5000,5,"White",14,14,14,7,2,2,0,0,19 +66,130,1,40000,40,"Black",14,14,14,8,7,1,0,0,34 +62,124,0,6000,6,"Black",13,13,13,7,1,2,7,7,26 +71,170,1,1e+05,100,"White",18,18,NA,8,5,2,0,0,77 +65,160,0,5000,5,"Black",16,16,16,8,1,2,7,7,30 +64,190,0,45000,45,"White",8,NA,NA,8,1,1,7,7,52 +60,120,0,25000,25,"Black",12,12,12,8,5,2,0,0,26 +66,156,1,110000,110,"White",18,18,18,5,5,2,0,0,37 +61,102,0,25000,25,"White",13,13,13,8,4,1,2,2,37 +72,145,1,41000,41,"Hispanic",13,NA,NA,8,7,2,0,0,32 +70,145,0,25000,25,"White",12,12,NA,5,6,2,0,0,55 +63,130,0,23000,23,"White",13,13,13,4,4,2,0,0,78 +68,132,0,15000,15,"White",14,NA,14,8,5,2,0,0,78 +63,120,0,0,0,"White",12,12,12,7,5,2,7,7,32 +70,165,1,21000,21,"White",12,12,12,8,7,1,1,1,23 +62,150,0,4000,4,"White",12,12,12,5,1,1,7,7,29 +71,280,1,25000,25,"White",12,12,12,8,4,1,0,0,36 +70,170,1,30000,30,"White",18,18,18,4,7,1,1,1,46 +64,159,0,14000,14,"White",11,11,NA,8,1,2,0,0,51 +63,115,0,6000,6,"White",12,12,12,3,2,1,7,7,35 +65,144,0,14000,14,"White",12,12,12,2,1,1,0,0,46 +71,175,1,43000,43,"White",12,12,12,1,6,2,6,6,27 +62,128,0,25000,25,"White",15,15,15,8,5,1,7,7,33 +73,195,1,40000,40,"White",12,12,12,8,1,2,0,0,66 +64,135,0,25000,25,"White",16,16,16,8,1,2,0,0,73 +68,220,1,65000,65,"White",17,17,17,5,5,2,3,3,40 +76,210,1,16000,16,"White",15,15,15,3,4,2,0,0,32 +73,196,1,136500,136.5,"White",16,16,16,1,1,1,0,0,65 +70,160,1,87000,87,"White",18,NA,NA,1,6,2,0,0,54 +66,120,0,8000,8,"White",12,12,12,8,1,2,0,0,71 +64,NA,0,20000,20,"White",15,15,15,4,4,2,4,4,39 +60,NA,0,14000,14,"White",14,14,14,1,1,2,0,0,72 +68,140,1,45000,45,"White",12,12,12,8,1,2,0,0,74 +61,180,0,8000,8,"White",11,NA,NA,1,1,2,0,0,72 +65,185,0,15000,15,"White",10,NA,10,3,1,1,0,0,71 +66,130,1,12000,12,"White",12,12,NA,5,4,1,0,0,28 +63,132,0,8000,8,"White",14,14,14,5,5,2,0,0,31 +63,105,0,16000,16,"White",15,15,15,1,1,2,2,2,32 +67,NA,0,25000,25,"White",12,NA,NA,1,2,2,0,0,43 +74,170,1,6000,6,"White",15,15,15,7,1,1,7,7,73 +66,160,0,136500,136.5,"White",12,NA,12,4,7,2,1,1,45 +70,180,1,19000,19,"White",12,12,12,8,6,2,0,0,32 +68,155,0,21000,21,"White",13,13,13,6,3,1,5,5,39 +70,131,0,43000,43,"White",18,18,18,7,3,2,1,1,46 +69,190,1,35000,35,"White",15,15,15,7,7,2,0,0,21 +70,175,1,8000,8,"White",10,NA,NA,8,2,2,0,0,75 +63,125,0,21000,21,"White",14,14,14,7,1,1,1,1,41 +65,135,0,5800,5.8,"White",12,12,12,8,5,2,5,5,30 +69,185,1,17000,17,"White",12,NA,NA,5,1,2,0,0,46 +65,120,0,45000,45,"White",12,NA,NA,2,2,1,2,2,42 +68,140,1,24000,24,"White",14,14,14,4,3,1,2,2,49 +62,140,0,5000,5,"White",11,11,NA,1,1,2,3,3,71 +70,185,1,62000,62,"White",11,11,11,1,1,2,0,0,48 +66,150,0,11000,11,"White",12,12,12,8,1,1,3,3,23 +65,225,1,10000,10,"White",13,NA,13,5,1,2,0,0,27 +70,185,1,40000,40,"White",14,14,14,4,4,2,0,0,36 +66,163,0,0,0,"Black",12,NA,12,8,5,2,0,0,37 +70,170,1,40000,40,"White",12,NA,NA,8,4,1,0,0,47 +66,165,0,24000,24,"Black",14,NA,NA,8,2,2,3,3,29 +68,160,1,50000,50,"Black",18,18,18,8,7,2,0,0,34 +68,NA,0,25000,25,"White",12,12,12,6,2,1,3,3,25 +68,160,1,24000,24,"White",16,16,16,1,3,2,0,0,26 +68,120,1,20000,20,"White",16,16,16,8,3,2,0,0,33 +63,120,0,15000,15,"White",16,16,16,8,5,2,0,0,23 +70,195,1,60000,60,"White",18,18,18,3,1,2,0,0,50 +65,155,0,11000,11,"White",13,13,13,5,1,2,0,0,47 +64,115,0,5000,5,"White",15,15,15,8,2,2,7,7,40 +63,113,0,136500,136.5,"White",17,17,17,8,6,2,0,0,84 +69,180,1,87000,87,"White",18,18,18,8,5,2,5,5,39 +65,135,0,27000,27,"White",16,16,16,7,5,2,0,0,30 +77,241,1,89000,89,"White",16,16,16,8,1,2,2,2,41 +70,175,1,40000,40,"White",14,14,14,8,4,2,2,2,28 +64,120,0,15000,15,"White",16,16,16,8,7,2,0,0,26 +64,130,0,1000,1,"White",14,14,14,8,6,2,0,0,20 +62,180,0,0,0,"White",12,12,12,4,1,1,7,7,28 +64,NA,0,22000,22,"White",12,12,12,5,1,2,0,0,60 +64,184,0,12000,12,"White",8,8,8,1,1,1,0,0,48 +63,125,0,22000,22,"White",16,16,16,4,2,2,2,2,28 +58,180,0,40000,40,"Black",12,12,NA,8,1,2,0,0,56 +73,182,1,25000,25,"Black",10,NA,NA,2,6,2,2,2,55 +66,182,0,0,0,"White",12,12,12,8,6,2,0,0,58 +64,120,0,62000,62,"White",16,16,16,7,7,2,3,3,40 +62,150,0,40000,40,"White",16,16,16,5,1,2,0,0,44 +61,123,0,0,0,"White",13,13,13,6,7,2,0,0,42 +64,113,0,35000,35,"Hispanic",14,14,14,4,2,2,0,0,53 +64,119,0,7000,7,"White",12,12,12,8,1,2,0,0,28 +70,190,1,25000,25,"White",14,14,NA,8,1,2,0,0,40 +62,118,0,14000,14,"White",12,12,12,6,2,2,0,0,37 +62,120,0,5000,5,"White",12,12,12,8,1,2,1,1,20 +64,150,0,15000,15,"White",12,12,12,2,1,2,0,0,56 +66,240,0,0,0,"Black",14,14,14,1,1,2,0,0,31 +66,150,0,6000,6,"White",13,13,13,7,6,2,0,0,34 +69,223,0,11000,11,"Black",12,NA,NA,1,1,2,7,7,41 +64,132,0,10000,10,"White",13,13,13,4,1,2,0,0,31 +62,168,0,0,0,"White",12,12,NA,8,1,2,1,1,59 +62,118,0,5000,5,"White",12,12,12,4,4,1,4,4,32 +71,193,1,20000,20,"White",14,14,14,8,5,2,2,2,41 +59,108,0,35000,35,"White",12,NA,NA,7,1,2,0,0,56 +62,155,0,7000,7,"White",12,12,12,4,1,2,0,0,73 +68,185,1,38000,38,"White",9,9,9,8,2,2,1,1,46 +68,175,1,29000,29,"White",9,NA,NA,4,1,1,1,1,58 +62,122,0,20000,20,"White",10,10,NA,4,1,2,0,0,44 +63,160,0,8000,8,"White",12,12,12,4,1,1,0,0,57 +69,175,1,36000,36,"White",16,16,16,8,1,2,0,0,51 +67,228,0,1500,1.5,"White",12,12,12,7,7,2,1,1,44 +64,135,0,42000,42,"White",18,18,18,6,5,2,1,1,29 +68,135,0,35000,35,"White",17,17,17,8,1,1,1,1,44 +70,165,1,25000,25,"White",12,12,12,1,7,1,0,0,22 +76,150,1,5000,5,"White",9,9,9,3,6,2,0,0,18 +69,140,1,13000,13,"White",10,10,10,1,1,1,0,0,20 +66,133,0,20000,20,"White",11,11,11,4,1,2,0,0,64 +66,98,0,10000,10,"White",12,NA,NA,8,1,2,1,1,71 +72,194,1,50000,50,"Other",15,15,15,8,5,1,3,3,49 +69,145,1,30000,30,"Black",11,11,11,8,1,2,0,0,51 +69,160,1,7000,7,"White",12,NA,NA,7,6,2,0,0,23 +62,118,0,15000,15,"Black",12,12,12,8,1,2,0,0,82 +60,200,0,31000,31,"Black",12,NA,NA,8,1,1,7,7,48 +66,149,0,15000,15,"Black",12,12,12,2,2,2,3,3,42 +60,135,0,0,0,"White",18,18,NA,2,1,2,4,4,41 +67,170,1,50000,50,"White",16,16,16,7,2,2,1,1,49 +67,120,0,5000,5,"Hispanic",11,11,11,1,1,2,3,3,18 +66,140,1,5000,5,"White",15,15,15,8,7,2,0,0,20 +70,150,0,600,0.6,"Black",12,12,12,7,6,2,3,3,18 +64,150,0,14000,14,"Black",8,8,NA,8,1,2,0,0,51 +60,105,0,40000,40,"Other",18,18,18,8,1,2,0,0,35 +68,170,1,24000,24,"White",18,18,18,5,7,2,5,5,36 +66,150,0,25000,25,"Black",12,NA,NA,8,1,2,0,0,59 +73,180,1,22000,22,"Black",12,12,NA,1,5,1,7,7,24 +72,215,1,20000,20,"White",8,8,8,4,1,1,1,1,36 +64,145,0,20112,20.112,"White",12,NA,NA,8,5,1,3,3,38 +67,135,1,12000,12,"White",13,13,13,7,1,1,1,1,67 +71,180,1,15000,15,"Black",8,NA,NA,8,6,1,0,0,37 +70,221,1,20000,20,"White",18,18,18,7,7,1,0,0,69 +66,129,0,5000,5,"White",8,8,8,4,1,2,0,0,44 +67,140,0,41000,41,"White",13,13,13,7,1,2,1,1,40 +71,155,1,13000,13,"Black",9,9,9,8,1,2,0,0,50 +63,136,0,0,0,"White",12,12,12,5,5,2,3,3,25 +73,170,1,60000,60,"White",16,16,16,1,4,1,0,0,31 +70,155,1,24000,24,"White",16,16,16,8,7,2,4,4,25 +70,165,1,38000,38,"White",16,16,16,1,7,2,6,6,36 +71,128,0,3000,3,"White",14,14,14,3,2,2,4,4,27 +66,110,0,13000,13,"White",12,12,12,4,2,1,0,0,30 +75,160,1,5000,5,"White",12,12,12,1,2,1,2,2,21 +60,92,0,20000,20,"White",14,14,14,4,5,2,5,5,37 +72,230,1,22000,22,"White",12,12,12,4,7,2,5,5,28 +70,256,0,35000,35,"White",14,14,14,1,1,2,2,2,40 +63,118,0,0,0,"Black",16,16,16,3,7,2,1,1,23 +75,230,1,28000,28,"Black",9,NA,NA,8,4,2,0,0,55 +60,110,0,22000,22,"White",12,12,12,6,3,1,7,7,41 +73,186,1,30000,30,"Black",12,NA,12,8,5,2,1,1,44 +65,165,1,5000,5,"Black",6,NA,NA,8,1,2,0,0,70 +65,210,0,30000,30,"Black",12,12,NA,2,1,2,7,7,32 +63,135,0,35000,35,"White",17,17,17,8,1,2,0,0,63 +67,140,1,30000,30,"White",16,16,16,8,4,2,0,0,31 +61,130,0,32000,32,"White",12,12,12,8,1,2,0,0,69 +69,135,0,26000,26,"White",17,17,17,6,5,2,4,4,43 +64,144,0,22000,22,"White",14,14,14,4,6,1,1,1,34 +62,190,0,15000,15,"White",14,NA,NA,5,1,2,0,0,72 +70,150,1,25000,25,"White",12,12,12,6,5,2,0,0,33 +68,147,0,11000,11,"White",10,10,10,8,3,1,7,7,24 +67,140,1,15000,15,"White",12,NA,NA,8,1,2,0,0,33 +62,130,0,13000,13,"White",12,NA,NA,5,1,1,1,1,53 +64,180,0,10000,10,"White",15,15,15,7,7,1,1,1,42 +68,110,0,0,0,"White",12,12,12,1,1,2,7,7,24 +72,200,1,35000,35,"White",16,16,16,8,6,2,0,0,32 +68,120,0,12000,12,"White",12,12,12,4,4,2,0,0,45 +64,130,0,25000,25,"White",17,17,17,6,1,2,7,7,38 +66,130,1,0,0,"White",13,13,13,5,7,1,0,0,57 +64,118,0,7000,7,"White",11,NA,NA,8,1,1,0,0,64 +73,230,1,57000,57,"White",14,14,14,2,1,1,0,0,37 +73,210,1,36000,36,"White",16,16,16,8,4,2,2,2,37 +69,175,1,29000,29,"Hispanic",14,14,14,7,6,2,4,4,29 +68,133,0,8000,8,"White",13,13,13,8,4,2,2,2,19 +71,125,1,3000,3,"Black",11,11,11,8,1,2,4,4,18 +63,160,0,0,0,"White",12,12,12,5,2,2,0,0,64 +66,205,0,20000,20,"White",16,16,16,8,1,2,0,0,41 +66,158,0,0,0,"White",12,NA,NA,8,1,1,3,3,36 +66,173,1,33000,33,"White",12,12,12,7,4,2,1,1,57 +68,210,0,15000,15,"Hispanic",12,12,NA,8,1,2,0,0,68 +70,235,1,16000,16,"White",12,12,12,1,1,2,1,1,33 +62,148,0,5000,5,"White",12,12,12,6,7,2,2,2,78 +66,142,0,8000,8,"White",14,14,14,5,4,2,3,3,43 +63,122,0,32000,32,"Black",16,16,16,4,1,2,3,3,34 +75,175,1,14500,14.5,"White",12,12,12,1,3,1,0,0,24 +67,125,0,13000,13,"White",12,12,12,2,2,2,6,6,29 +68,115,1,5000,5,"White",16,16,16,4,5,2,0,0,27 +60,NA,0,5000,5,"Black",12,12,12,2,1,2,0,0,34 +62,125,0,0,0,"White",10,NA,NA,8,7,2,2,2,20 +70,200,0,5000,5,"White",11,NA,11,4,1,2,1,1,57 +63,160,0,7000,7,"White",9,9,9,7,4,2,1,1,25 +65,126,0,50000,50,"Black",18,18,18,7,1,2,0,0,65 +69,185,0,12000,12,"Black",12,12,12,8,2,1,3,3,35 +71,209,1,19000,19,"White",14,14,14,8,6,2,0,0,61 +62,110,0,9000,9,"White",12,12,12,8,7,1,0,0,55 +64,110,0,25000,25,"White",12,12,12,2,2,1,4,4,38 +65,130,0,20000,20,"Black",12,NA,NA,8,1,1,2,2,35 +72,170,1,55000,55,"Hispanic",18,18,18,1,1,2,0,0,35 +62,145,0,15000,15,"Black",12,NA,NA,2,1,2,0,0,71 +75,190,1,45000,45,"White",18,18,18,6,7,1,4,4,31 +65,120,0,10000,10,"White",12,12,12,8,7,1,0,0,40 +65,142,0,15000,15,"White",12,12,12,8,1,2,0,0,67 +63,113,0,13000,13,"White",12,12,12,2,2,1,0,0,19 +66,120,0,45000,45,"White",18,18,18,7,7,2,0,0,30 +64,110,0,20000,20,"White",13,13,13,1,1,1,7,7,31 +68,116,0,45000,45,"White",16,16,16,6,2,2,6,6,29 +72,185,1,30000,30,"White",12,12,12,8,6,2,0,0,26 +64,110,0,12000,12,"White",12,12,12,8,1,2,1,1,34 +70,125,0,26000,26,"White",13,NA,13,7,2,2,2,2,33 +65,115,0,12500,12.5,"White",12,12,12,3,6,1,1,1,27 +64,130,0,8000,8,"White",12,12,12,2,1,1,1,1,29 +64,120,0,15000,15,"Hispanic",16,16,16,2,6,2,7,7,32 +67,207,1,65000,65,"White",14,14,14,2,7,1,1,1,25 +73,175,1,25000,25,"White",10,NA,10,8,6,1,6,6,21 +73,185,1,8000,8,"Hispanic",14,14,14,4,6,2,1,1,21 +65,110,1,15000,15,"Other",14,14,14,7,4,2,1,1,21 +64,160,0,12000,12,"White",16,16,16,4,1,1,1,1,40 +72,195,1,35000,35,"White",12,12,12,8,1,2,2,2,42 +67,140,0,35000,35,"Black",13,13,13,5,6,2,2,2,37 +67,162,1,40000,40,"White",16,16,16,7,6,2,0,0,31 +66,140,0,15000,15,"Hispanic",14,14,14,7,2,2,1,1,24 +74,145,1,29000,29,"White",12,12,12,8,4,2,0,0,22 +60,114,0,5000,5,"White",10,10,10,8,1,1,0,0,74 +64,96,0,15000,15,"White",12,12,12,5,4,1,7,7,33 +63,175,0,15000,15,"White",13,13,13,4,2,2,1,1,31 +74,250,1,20000,20,"White",12,NA,NA,4,2,2,1,1,36 +74,205,1,3000,3,"Black",6,NA,NA,8,5,2,0,0,62 +63,120,0,1000,1,"Black",16,16,16,8,2,2,5,5,19 +62,140,0,8000,8,"Black",11,11,11,3,2,1,7,7,23 +62,103,0,5000,5,"White",12,12,NA,4,6,1,1,1,18 +67,160,0,25000,25,"White",16,16,16,8,5,2,2,2,27 +75,219,1,5000,5,"White",13,13,13,7,5,1,0,0,22 +69,163,1,20000,20,"White",12,12,12,7,4,2,0,0,57 +65,133,0,15000,15,"White",12,12,12,2,1,1,0,0,26 +73,150,1,30000,30,"White",12,12,12,2,2,2,0,0,34 +63,200,0,12000,12,"White",12,NA,12,1,1,1,0,0,35 +59,NA,0,5000,5,"White",11,NA,NA,1,1,2,3,3,80 +60,120,0,0,0,"White",12,12,12,7,1,1,7,7,34 +65,122,0,15000,15,"White",14,14,14,8,7,2,2,2,38 +64,145,1,5000,5,"Black",14,14,14,4,1,2,0,0,34 +64,130,0,15000,15,"Black",10,NA,NA,5,2,2,1,1,59 +64,135,0,25000,25,"White",18,NA,NA,8,1,2,0,0,78 +67,210,0,10000,10,"White",14,14,14,7,1,2,1,1,32 +69,140,1,16000,16,"White",12,12,12,8,1,1,0,0,19 +71,185,1,45000,45,"White",12,12,12,2,5,1,0,0,29 +72,170,1,40000,40,"White",14,14,14,5,5,2,0,0,54 +72,200,1,15000,15,"White",12,12,12,8,6,1,1,1,26 +63,140,0,0,0,"White",12,12,12,4,1,2,7,7,62 +66,152,0,20000,20,"White",13,13,13,8,5,1,0,0,33 +70,125,1,25000,25,"White",14,NA,NA,3,1,2,0,0,81 +64,145,0,19000,19,"White",14,14,14,7,5,1,0,0,52 +64,128,0,17600,17.6,"White",16,16,16,2,2,1,3,3,30 +68,155,1,7000,7,"White",12,NA,NA,8,1,2,0,0,67 +74,207,1,30000,30,"White",12,12,12,5,4,2,2,2,32 +62,125,0,18000,18,"White",11,11,11,1,1,1,0,0,47 +63,135,0,15000,15,"Hispanic",8,8,NA,7,1,1,0,0,41 +65,135,0,25000,25,"White",16,16,16,4,2,1,2,2,47 +66,155,0,0,0,"White",14,14,14,6,1,2,1,1,55 +60,120,0,6000,6,"White",5,5,5,8,1,2,7,7,62 +69,170,1,70000,70,"White",18,18,18,7,6,2,0,0,42 +61,115,0,15000,15,"Other",16,16,16,5,1,2,0,0,34 +68,140,1,15000,15,"White",12,12,12,8,1,1,0,0,61 +65,135,0,25000,25,"White",17,17,17,8,1,1,0,0,33 +66,120,0,35000,35,"White",16,16,16,4,6,2,0,0,28 +70,155,1,18000,18,"White",16,16,16,5,3,2,0,0,24 +72,165,1,28000,28,"Black",15,15,15,2,6,2,0,0,30 +66,160,0,35000,35,"White",12,12,12,8,1,1,0,0,49 +67,150,1,25000,25,"Hispanic",12,12,12,8,4,2,1,1,23 +64,135,0,15000,15,"Hispanic",11,11,11,8,6,2,0,0,21 +71,172,1,22000,22,"Hispanic",14,14,NA,7,2,1,0,0,28 +63,128,0,0,0,"White",12,12,12,8,6,2,0,0,29 +73,190,1,35000,35,"White",12,NA,NA,3,3,2,0,0,30 +64,140,0,18000,18,"Black",15,NA,15,1,6,2,0,0,46 +68,150,1,35000,35,"White",14,14,14,7,5,1,0,0,37 +64,115,0,16400,16.4,"Black",12,12,12,4,1,2,5,5,21 +66,135,1,22000,22,"Black",16,16,16,1,1,1,1,1,37 +67,128,0,30000,30,"White",16,NA,NA,4,1,2,0,0,58 +64,135,0,17000,17,"Hispanic",12,12,12,4,5,2,2,2,27 +64,147,0,25000,25,"Black",14,14,14,8,6,2,7,7,36 +62,138,0,10000,10,"White",12,12,12,6,1,1,3,3,51 +69,180,1,40000,40,"White",12,12,12,1,3,2,1,1,37 +63,125,0,12500,12.5,"White",12,12,12,2,1,2,0,0,63 +63,180,0,15000,15,"White",12,NA,NA,1,1,2,0,0,77 +63,135,0,10000,10,"White",12,12,NA,7,3,2,7,7,30 +72,195,1,35000,35,"White",15,NA,NA,1,1,2,3,3,45 +61,93,0,0,0,"Hispanic",16,16,16,8,6,2,2,2,23 +75,202,1,105000,105,"White",12,12,12,2,2,1,1,1,49 +71,160,1,25000,25,"White",12,12,12,2,1,1,1,1,27 +70,170,1,1e+05,100,"White",18,18,18,8,7,2,1,1,40 +60,130,0,25000,25,"White",12,NA,NA,1,1,1,0,0,61 +69,158,1,21000,21,"White",12,NA,12,1,1,1,0,0,51 +64,200,0,10000,10,"White",14,14,14,1,1,2,7,7,56 +72,222,1,33000,33,"White",12,12,12,2,1,1,3,3,26 +69,149,1,26000,26,"White",18,18,18,1,7,2,0,0,25 +63,136,0,60000,60,"White",10,10,NA,7,1,2,0,0,78 +64,110,0,15000,15,"White",16,16,16,8,5,2,0,0,84 +71,235,1,18000,18,"White",16,16,16,7,7,2,1,1,45 +59,105,0,15000,15,"White",8,NA,NA,8,1,1,0,0,61 +68,170,1,5000,5,"White",13,13,13,6,4,2,0,0,20 +77,270,1,60000,60,"White",17,17,17,8,2,2,0,0,42 +68,150,0,12000,12,"White",14,14,14,8,1,2,3,3,69 +70,140,1,28000,28,"Black",18,18,18,8,1,2,0,0,38 +69,154,1,42000,42,"White",18,18,18,5,6,1,0,0,43 +63,103,0,2000,2,"White",12,12,12,8,1,1,0,0,33 +65,147,0,10000,10,"White",16,16,16,1,1,2,1,1,54 +73,190,1,20000,20,"Black",18,18,18,8,6,2,0,0,33 +66,145,1,28000,28,"Other",15,15,15,8,1,2,0,0,40 +72,212,1,10000,10,"Black",17,17,17,4,2,1,0,0,62 +66,164,1,0,0,"White",16,NA,NA,8,1,2,0,0,65 +72,161,1,31000,31,"Black",12,12,12,8,6,1,7,7,31 +69,172,0,17000,17,"Black",13,13,13,7,1,2,4,4,37 +67,220,0,16000,16,"White",12,NA,NA,4,1,2,3,3,39 +66,170,0,35000,35,"White",15,15,15,8,1,2,0,0,38 +67,111,0,3000,3,"White",12,12,12,4,1,1,7,7,26 +68,149,0,5000,5,"White",11,11,11,7,6,1,1,1,78 +72,155,1,25000,25,"White",10,NA,NA,1,1,1,0,0,51 +68,150,0,16000,16,"White",18,18,18,8,6,2,4,4,39 +65,120,0,35000,35,"Black",15,15,15,8,7,2,3,3,42 +62,140,0,27000,27,"Black",17,17,17,5,1,2,0,0,33 +69,155,1,25000,25,"White",17,17,17,5,5,2,1,1,29 +62,200,0,0,0,"White",14,14,14,8,1,2,1,1,78 +70,145,1,40000,40,"White",16,16,16,4,4,1,1,1,41 +66,151,0,45000,45,"White",16,16,16,5,2,2,0,0,43 +66,185,1,14000,14,"White",12,12,NA,7,1,2,2,2,23 +66,200,0,25000,25,"White",14,14,14,8,1,1,0,0,37 +72,230,1,40000,40,"White",12,12,12,7,5,2,0,0,42 +69,187,1,34000,34,"White",12,NA,NA,6,1,1,0,0,35 +66,205,1,40000,40,"White",12,NA,12,7,2,2,0,0,34 +71,190,1,25000,25,"White",16,16,16,6,1,2,0,0,83 +69,165,1,35000,35,"White",14,14,14,1,7,2,0,0,28 +60,104,0,12000,12,"Hispanic",12,12,12,8,1,1,0,0,51 +65,NA,0,30000,30,"White",17,17,17,8,3,2,4,4,43 +62,180,0,23000,23,"White",12,12,12,2,1,1,6,6,40 +67,150,0,2000,2,"White",12,12,12,4,2,2,3,3,30 +67,175,1,20000,20,"White",14,14,14,8,6,1,0,0,25 +68,240,0,10000,10,"Black",9,9,NA,3,1,2,0,0,62 +65,175,0,0,0,"Black",6,NA,NA,1,1,2,4,4,67 +63,115,0,25000,25,"White",16,16,16,2,1,2,0,0,33 +64,210,0,5000,5,"Other",12,12,12,1,1,2,7,7,19 +66,150,0,5000,5,"Black",11,NA,NA,8,1,1,0,0,64 +66,160,0,60000,60,"Black",16,16,16,8,1,2,0,0,43 +74,170,1,12000,12,"Black",16,16,NA,4,1,1,3,3,41 +65,157,0,25000,25,"White",18,18,18,2,1,2,1,1,61 +63,180,0,22000,22,"Black",14,14,14,2,1,2,0,0,73 +62,130,0,0,0,"White",12,12,12,4,1,1,2,2,38 +68,165,1,8000,8,"White",17,17,17,2,2,2,0,0,25 +68,NA,0,5000,5,"White",17,17,17,8,7,2,0,0,22 +66,124,0,2000,2,"White",16,16,16,7,6,2,1,1,21 +64,110,0,5000,5,"White",14,14,14,8,2,2,0,0,30 +61,130,0,10000,10,"White",13,13,13,7,1,2,0,0,20 +65,122,0,18600,18.6,"White",16,16,16,6,6,2,0,0,26 +62,120,0,20000,20,"White",14,14,14,8,7,2,0,0,20 +73,200,1,1e+05,100,"White",18,18,18,2,1,2,0,0,37 +62,135,0,50000,50,"White",15,15,15,1,1,1,2,2,40 +70,170,1,27000,27,"White",12,12,12,6,5,2,1,1,42 +58,100,0,1000,1,"Black",12,12,12,8,1,1,0,0,58 +68,145,1,18000,18,"White",12,12,12,4,2,1,4,4,20 +67,140,0,17000,17,"White",14,14,14,4,1,1,7,7,23 +64,180,0,10000,10,"White",12,12,12,8,1,2,0,0,74 +70,208,1,14000,14,"White",14,NA,NA,1,1,2,0,0,35 +72,200,1,7200,7.2,"White",14,NA,NA,8,1,1,0,0,66 +63,130,0,0,0,"Other",8,8,8,4,1,1,3,3,52 +63,112,0,33000,33,"White",17,17,17,7,2,2,0,0,39 +66,180,1,23000,23,"White",12,12,12,1,1,2,0,0,34 +65,138,0,10000,10,"White",12,12,12,4,1,2,0,0,41 +61,124,1,22000,22,"White",12,12,12,2,6,2,2,2,24 +61,110,0,13000,13,"Hispanic",12,12,NA,7,1,2,2,2,19 +67,150,0,33000,33,"White",12,12,12,8,6,2,3,3,31 +73,250,1,36000,36,"White",12,12,12,7,1,1,0,0,36 +66,180,0,10000,10,"Black",10,NA,10,8,1,2,0,0,64 +71,185,0,10000,10,"Black",14,14,14,4,1,2,0,0,32 +64,145,0,6000,6,"White",12,12,12,5,3,2,1,1,60 +70,199,1,25000,25,"White",11,NA,NA,8,1,2,0,0,63 +67,165,0,12000,12,"White",12,12,12,8,5,2,3,3,43 +62,190,0,10000,10,"White",11,NA,NA,5,1,1,1,1,47 +67,131,0,21000,21,"White",12,12,12,6,1,2,2,2,45 +69,210,1,26000,26,"White",12,12,12,5,1,2,1,1,32 +66,170,0,22000,22,"Black",12,12,12,8,1,1,0,0,50 +66,155,0,23000,23,"Black",15,15,15,4,1,2,0,0,54 +66,150,1,20000,20,"White",15,15,15,8,7,2,1,1,24 +66,130,0,10000,10,"White",13,13,13,4,1,2,0,0,38 +64,137,0,15000,15,"White",12,NA,NA,2,1,2,0,0,71 +72,190,1,7000,7,"Black",14,14,14,5,5,2,1,1,24 +64,195,0,15000,15,"White",12,12,12,7,1,2,2,2,38 +64,170,0,0,0,"White",12,12,12,6,1,2,2,2,60 +65,160,0,26000,26,"White",16,16,16,1,1,1,0,0,34 +72,150,1,10000,10,"White",11,11,11,7,5,1,0,0,31 +63,150,0,0,0,"White",8,8,8,1,1,2,0,0,57 +71,185,1,3000,3,"White",14,14,14,8,5,2,1,1,20 +64,135,0,27000,27,"Hispanic",17,17,17,2,2,2,1,1,41 +70,190,1,25000,25,"Black",16,16,16,5,4,1,0,0,52 +66,125,0,35000,35,"White",18,18,18,8,1,2,0,0,39 +64,112,0,28000,28,"White",17,17,17,5,7,2,7,7,25 +69,154,0,25000,25,"White",12,12,12,1,7,1,1,1,22 +67,123,0,15000,15,"White",12,12,12,8,6,2,1,1,27 +75,178,1,55000,55,"White",18,18,18,8,7,2,0,0,30 +66,125,0,20000,20,"Hispanic",17,17,17,8,7,2,0,0,26 +67,125,0,8500,8.5,"White",12,12,12,8,1,1,0,0,44 +68,132,0,0,0,"White",12,12,12,1,1,2,0,0,58 +67,142,0,15000,15,"White",13,13,13,5,2,1,0,0,31 +75,214,1,30000,30,"Black",8,NA,NA,6,5,1,0,0,41 +71,175,1,30000,30,"White",16,16,16,1,1,2,0,0,30 +62,175,0,0,0,"White",12,12,12,8,1,2,0,0,66 +68,180,0,5000,5,"White",13,13,13,6,7,2,2,2,54 +67,124,0,5000,5,"White",14,14,14,2,3,1,0,0,18 +68,135,0,20000,20,"White",12,12,12,7,7,2,1,1,31 +70,183,0,20000,20,"White",15,NA,15,7,1,2,1,1,57 +70,151,1,22000,22,"White",6,6,6,5,1,2,0,0,75 +67,145,1,25000,25,"White",16,16,16,1,6,2,0,0,26 +64,122,0,0,0,"White",16,16,16,1,1,1,0,0,62 +64,140,0,5000,5,"Black",12,NA,NA,7,2,2,3,3,33 +65,120,0,15000,15,"White",12,12,12,8,1,1,0,0,64 +71,160,1,3000,3,"White",8,8,8,8,4,2,2,2,22 +63,137,0,16000,16,"White",12,12,12,6,1,1,0,0,49 +70,175,1,30000,30,"White",14,14,14,8,6,2,1,1,27 +64,126,0,0,0,"White",12,12,12,8,1,2,0,0,57 +61,148,0,10000,10,"Black",12,12,NA,1,1,2,0,0,39 +65,162,0,15000,15,"Black",12,12,12,1,5,2,7,7,28 +67,170,1,28000,28,"White",12,12,12,1,2,2,0,0,46 +67,150,0,15000,15,"White",12,NA,NA,2,2,2,2,2,45 +68,NA,0,15000,15,"White",12,12,12,6,1,2,3,3,69 +59,110,0,5000,5,"White",6,NA,NA,8,1,2,0,0,76 +63,135,0,5000,5,"White",12,NA,NA,7,7,1,7,7,53 +65,153,1,31500,31.5,"White",14,14,14,2,4,2,0,0,35 +66,168,1,95000,95,"White",18,18,18,7,2,2,3,3,52 +68,160,1,45000,45,"White",17,17,17,7,1,1,0,0,61 +69,150,0,20000,20,"White",12,NA,NA,4,1,2,0,0,53 +67,145,1,38000,38,"White",12,12,12,1,2,1,7,7,40 +72,250,1,10000,10,"White",8,8,NA,8,1,2,0,0,70 +63,139,0,15000,15,"White",16,16,16,7,1,2,0,0,73 +74,199,1,30000,30,"White",12,12,12,8,1,2,5,5,41 +74,225,1,35900,35.9,"White",16,16,16,4,6,2,0,0,42 +66,104,0,12000,12,"White",13,13,NA,1,7,2,1,1,22 +72,165,1,15000,15,"White",15,15,15,2,1,2,7,7,35 +69,115,0,10000,10,"White",16,16,16,2,2,1,0,0,25 +66,150,0,45000,45,"White",18,18,18,7,5,2,0,0,44 +62,175,0,5000,5,"White",12,12,12,4,5,2,3,3,19 +68,130,1,5000,5,"White",11,11,11,8,1,1,0,0,25 +74,185,1,40000,40,"White",16,16,16,8,6,2,0,0,56 +72,180,1,21500,21.5,"White",12,12,12,8,6,1,4,4,27 +66,132,1,14000,14,"White",12,NA,NA,8,1,1,4,4,62 +67,175,1,38000,38,"Other",17,17,17,7,4,2,0,0,54 +65,130,0,1000,1,"White",12,12,12,8,7,2,0,0,18 +66,240,1,14000,14,"White",12,12,NA,8,1,2,4,4,73 +65,130,0,15000,15,"White",12,12,12,8,2,1,1,1,31 +64,110,0,15000,15,"White",16,16,16,6,2,1,0,0,23 +62,132,0,0,0,"Hispanic",12,NA,NA,8,1,2,0,0,63 +64,160,0,25000,25,"White",12,NA,NA,4,1,2,0,0,70 +68,145,0,24000,24,"White",13,13,13,7,6,2,0,0,42 +64,130,0,4500,4.5,"White",16,16,16,8,4,1,4,4,23 +64,127,0,18000,18,"White",16,16,16,7,5,2,0,0,63 +64,115,0,35000,35,"White",12,12,12,8,7,2,0,0,19 +63,100,0,14000,14,"White",12,NA,12,2,2,2,0,0,20 +69,160,0,10000,10,"White",12,12,12,1,1,2,7,7,28 +67,150,0,9500,9.5,"White",12,12,12,2,1,1,1,1,32 +63,140,0,11000,11,"White",15,15,15,1,1,2,0,0,66 +67,140,1,17000,17,"White",12,12,12,8,5,2,0,0,67 +60,130,0,6000,6,"White",13,13,13,8,6,2,0,0,28 +62,140,0,2500,2.5,"White",11,NA,NA,8,1,2,0,0,58 +72,163,1,40000,40,"White",16,16,16,7,5,2,0,0,41 +67,190,0,0,0,"White",14,14,14,6,5,2,2,2,35 +67,165,1,25000,25,"White",16,16,16,8,2,2,1,1,39 +68,170,0,15000,15,"White",13,13,13,8,1,2,2,2,65 +66,170,0,28000,28,"Black",15,15,15,8,2,1,0,0,60 +66,136,0,33000,33,"Black",12,12,12,8,1,2,1,1,45 +68,210,0,5000,5,"White",16,16,16,8,4,2,0,0,62 +60,149,0,4000,4,"White",8,NA,NA,8,1,2,7,7,64 +67,150,0,0,0,"White",12,12,NA,8,6,1,7,7,29 +65,130,1,4100,4.1,"White",16,16,16,5,2,1,0,0,30 +60,89,1,5000,5,"White",11,11,NA,1,1,2,0,0,76 +69,135,0,25000,25,"White",12,12,12,1,1,2,0,0,82 +72,205,1,32000,32,"White",12,12,NA,2,7,2,0,0,28 +65,170,1,15000,15,"Hispanic",9,9,9,8,1,1,0,0,40 +69,170,1,15000,15,"White",14,14,14,7,3,1,0,0,38 +64,140,0,13000,13,"White",8,NA,NA,8,1,1,0,0,58 +64,150,1,8000,8,"Hispanic",8,8,8,1,4,2,0,0,27 +62,100,0,0,0,"Other",17,17,17,1,1,2,3,3,26 +65,170,0,0,0,"White",13,13,13,5,4,2,0,0,56 +64,125,0,17000,17,"White",12,12,12,8,2,2,1,1,38 +67,137,0,15000,15,"White",12,12,12,8,1,2,0,0,77 +66,170,1,18000,18,"White",13,13,13,8,4,2,0,0,32 +73,165,1,12000,12,"White",12,12,12,7,7,2,1,1,24 +74,295,1,7000,7,"White",7,7,7,7,1,2,1,1,49 +66,121,0,0,0,"White",12,12,12,2,2,2,2,2,24 +65,130,0,1200,1.2,"White",14,14,14,6,3,2,1,1,22 +72,170,1,0,0,"White",12,12,12,6,7,2,0,0,18 +64,120,0,0,0,"White",12,12,12,6,4,2,2,2,18 +63,165,1,14000,14,"White",12,12,12,1,1,1,0,0,21 +63,115,0,17000,17,"White",12,12,12,2,1,1,3,3,40 +66,150,1,30000,30,"White",12,12,12,8,2,2,3,3,42 +69,196,1,5000,5,"White",6,6,6,8,1,2,0,0,61 +72,230,1,0,0,"White",10,NA,NA,1,4,2,0,0,63 +64,140,0,62000,62,"White",12,12,12,7,1,2,0,0,81 +70,260,1,25000,25,"White",12,NA,NA,4,1,2,0,0,53 +66,185,0,22000,22,"Hispanic",12,12,12,5,2,2,0,0,33 +63,130,0,15000,15,"White",12,12,12,5,4,1,2,2,21 +73,210,1,27000,27,"White",12,12,12,3,3,2,3,3,91 +63,135,0,20000,20,"White",16,16,16,3,5,2,0,0,26 +69,160,0,9000,9,"White",11,11,11,8,7,2,2,2,34 +66,120,0,0,0,"White",14,14,14,3,5,2,0,0,24 +73,168,1,17000,17,"White",12,12,NA,4,5,2,0,0,30 +65,119,0,5000,5,"White",14,14,14,8,1,2,4,4,21 +71,145,1,15000,15,"White",12,12,12,1,1,1,4,4,21 +68,160,0,1800,1.8,"White",12,12,12,6,1,2,7,7,46 +64,145,0,18000,18,"White",12,12,12,3,1,2,1,1,46 +63,120,0,25000,25,"White",18,18,18,8,1,2,0,0,42 +66,150,0,5000,5,"Black",14,14,14,8,6,2,2,2,47 +70,220,1,20000,20,"Black",16,16,16,8,5,2,2,2,41 +64,115,0,75000,75,"White",15,15,15,7,4,2,1,1,40 +66,170,0,3500,3.5,"White",12,12,12,6,3,2,0,0,40 +61,130,0,36000,36,"White",12,NA,12,8,1,2,0,0,71 +72,210,1,30000,30,"White",12,12,12,5,3,1,3,3,25 +65,145,0,25000,25,"White",13,13,13,1,7,1,0,0,78 +64,200,0,1000,1,"White",14,14,14,3,1,2,4,4,26 +68,187,1,60000,60,"White",12,NA,NA,8,1,2,0,0,66 +64,170,0,5000,5,"White",12,NA,NA,1,1,2,1,1,73 +74,195,1,35000,35,"White",13,NA,13,8,1,2,0,0,76 +67,160,1,9000,9,"White",13,13,13,8,1,1,0,0,33 +70,184,1,35000,35,"White",9,9,9,7,1,2,0,0,84 +66,150,0,11000,11,"White",10,10,10,6,1,1,0,0,58 +71,180,1,12000,12,"White",12,12,12,8,6,2,0,0,52 +71,170,1,30000,30,"White",12,12,12,7,4,1,0,0,43 +71,155,1,19000,19,"Black",7,NA,NA,8,1,1,0,0,57 +67,215,0,5000,5,"White",12,12,NA,2,1,2,0,0,46 +74,205,1,9000,9,"White",9,NA,NA,1,1,1,0,0,61 +75,225,1,30000,30,"White",16,16,16,7,2,2,0,0,29 +62,118,0,0,0,"White",12,12,12,4,1,2,5,5,33 +72,150,1,9000,9,"White",12,12,12,2,4,2,2,2,32 +66,145,0,15000,15,"Hispanic",16,16,16,6,5,2,0,0,30 +65,135,0,8000,8,"Black",12,12,12,8,5,2,3,3,31 +70,175,1,25000,25,"White",8,NA,NA,8,1,2,7,7,45 +66,129,0,10000,10,"White",10,10,10,4,1,2,0,0,75 +72,160,1,33000,33,"White",12,NA,12,8,4,2,1,1,37 +70,175,1,5000,5,"Black",10,NA,NA,8,7,2,0,0,60 +72,185,0,5000,5,"Black",5,NA,NA,1,1,2,0,0,83 +64,237,0,15000,15,"Black",9,NA,NA,8,1,2,0,0,65 +60,140,0,12000,12,"Hispanic",12,12,12,8,1,2,7,7,28 +64,136,0,18000,18,"White",15,15,15,3,4,1,2,2,37 +61,169,0,5000,5,"Hispanic",8,8,8,5,1,2,0,0,33 +66,181,0,15000,15,"Black",12,12,12,6,1,2,0,0,59 +65,193,0,30000,30,"White",13,13,13,7,1,2,0,0,61 +65,198,0,12500,12.5,"White",12,12,12,5,4,2,3,3,32 +62,145,0,10000,10,"Black",12,NA,12,1,1,2,0,0,36 +68,212,1,8500,8.5,"Black",13,13,13,1,1,2,0,0,71 +67,205,0,15000,15,"White",13,13,13,1,2,2,0,0,36 +73,175,1,21000,21,"Black",14,14,14,8,1,2,0,0,46 +63,122,0,0,0,"White",12,12,12,8,6,2,0,0,29 +64,153,0,21000,21,"White",12,12,12,2,1,2,0,0,77 +70,210,1,40000,40,"White",12,12,12,7,2,2,0,0,47 +66,135,0,0,0,"White",13,13,13,7,6,2,0,0,24 +68,160,0,21000,21,"White",17,17,17,4,2,2,0,0,25 +63,123,0,0,0,"White",13,13,13,2,5,2,4,4,39 +66,160,0,5000,5,"White",12,12,12,4,1,2,0,0,52 +71,153,0,22000,22,"White",17,17,17,2,1,2,2,2,36 +73,155,1,30000,30,"White",14,14,14,8,4,2,0,0,26 +64,185,0,0,0,"White",12,12,12,3,1,1,3,3,28 +61,140,0,123000,123,"White",14,14,14,8,3,2,0,0,58 +63,190,0,8000,8,"White",9,NA,9,8,1,2,4,4,45 +63,140,0,0,0,"White",9,NA,NA,1,1,1,1,1,54 +62,115,0,0,0,"White",8,8,8,7,1,1,0,0,56 +64,145,0,2000,2,"White",9,9,NA,3,1,2,0,0,25 +67,195,0,7600,7.6,"White",6,NA,6,5,1,2,0,0,62 +67,145,0,0,0,"White",12,12,12,1,1,2,2,2,18 +66,157,0,5000,5,"White",8,NA,NA,7,1,2,0,0,69 +72,160,1,15000,15,"White",14,14,14,7,5,2,2,2,22 +66,135,0,5000,5,"White",15,15,15,1,1,2,0,0,27 +66,135,0,15000,15,"Black",12,12,12,5,1,2,0,0,30 +61,114,0,0,0,"White",18,18,18,3,1,2,0,0,45 +63,138,0,10000,10,"White",12,12,12,2,1,2,4,4,25 +73,244,1,35000,35,"White",12,12,12,8,2,2,2,2,48 +64,130,0,15000,15,"White",12,12,12,1,1,2,7,7,26 +66,158,0,15000,15,"White",16,16,16,7,5,1,0,0,57 +70,155,0,4000,4,"White",12,12,12,8,3,1,0,0,22 +68,165,1,16000,16,"White",8,8,NA,2,6,2,0,0,24 +67,128,0,200,0.2,"White",12,12,12,7,1,2,0,0,33 +74,195,1,23000,23,"White",16,16,16,4,4,2,0,0,25 +64,123,0,16000,16,"White",16,16,16,8,5,1,2,2,27 +61,130,0,0,0,"White",12,12,12,2,1,2,1,1,27 +66,250,0,0,0,"White",12,12,12,1,1,2,0,0,52 +60,200,0,6000,6,"White",12,12,12,2,1,2,3,3,49 +59,125,0,600,0.6,"White",9,9,9,8,1,2,0,0,46 +62,160,0,0,0,"Black",16,16,16,5,1,2,1,1,36 +62,187,0,0,0,"Black",14,14,14,8,1,2,2,2,61 +62,124,0,25000,25,"Black",12,12,12,7,1,2,7,7,21 +62,210,0,0,0,"White",12,12,12,1,1,2,0,0,25 +75,201,1,28000,28,"Other",16,16,16,8,6,1,0,0,34 +66,155,0,15000,15,"White",8,NA,NA,6,1,1,NA,NA,47 +66,160,0,4000,4,"White",8,8,8,4,1,2,2,2,66 +64,129,1,15000,15,"White",12,12,12,8,1,1,2,2,35 +71,172,1,15000,15,"White",12,12,12,8,7,2,1,1,25 +66,150,0,25000,25,"White",18,18,18,5,2,2,0,0,36 +70,170,1,5000,5,"White",13,13,13,1,1,1,0,0,61 +61,117,0,0,0,"White",10,NA,NA,2,6,1,2,2,35 +63,123,0,25000,25,"White",12,12,12,4,5,1,0,0,30 +67,117,0,15000,15,"White",12,12,12,5,1,2,1,1,26 +74,230,0,15000,15,"White",12,12,NA,4,1,2,0,0,49 +69,180,1,40000,40,"White",11,NA,NA,8,7,1,0,0,44 +70,255,1,30000,30,"White",11,11,11,5,1,2,0,0,51 +66,195,0,5000,5,"White",12,12,12,8,1,1,7,7,29 +74,200,1,35000,35,"White",14,14,14,8,7,2,0,0,34 +65,200,0,16000,16,"White",14,14,14,2,1,2,3,3,31 +63,145,0,5000,5,"White",12,12,12,3,1,2,7,7,36 +64,128,0,28000,28,"White",16,16,16,7,7,2,0,0,40 +68,206,1,20000,20,"White",15,15,15,1,2,2,7,7,42 +66,140,1,21000,21,"White",13,13,13,8,7,1,7,7,30 +69,210,1,17000,17,"Black",12,NA,NA,7,4,1,2,2,42 +60,115,0,24000,24,"White",13,13,13,7,1,1,0,0,50 +61,110,0,25000,25,"White",12,12,12,8,1,2,0,0,75 +75,162,1,40000,40,"White",12,12,12,4,7,2,1,1,46 +70,220,1,15000,15,"White",9,9,9,2,2,2,0,0,25 +63,145,0,0,0,"Hispanic",9,9,9,8,3,2,7,7,23 +69,150,1,0,0,"White",13,13,13,6,6,2,0,0,20 +66,165,0,0,0,"White",16,16,16,7,1,2,0,0,63 +64,120,0,8000,8,"White",13,13,13,7,5,1,1,1,19 +63,175,0,19000,19,"Hispanic",15,15,15,1,1,1,0,0,45 +64,178,0,5000,5,"White",12,NA,12,1,1,2,0,0,76 +64,120,0,10000,10,"Hispanic",11,NA,NA,8,3,2,2,2,36 +67,138,0,45000,45,"White",16,16,16,7,6,1,0,0,69 +64,145,1,5000,5,"Black",17,17,17,8,1,2,0,0,33 +72,160,1,0,0,"White",14,14,14,7,5,2,0,0,21 +63,142,0,24000,24,"Black",14,14,14,4,5,2,1,1,40 +67,100,0,5000,5,"White",14,14,14,4,5,2,1,1,19 +63,155,0,15000,15,"Hispanic",14,14,14,4,5,2,1,1,42 +66,160,1,33000,33,"White",16,16,16,7,7,2,0,0,34 +65,125,0,24000,24,"White",14,14,14,8,1,2,0,0,24 +63,135,0,6000,6,"White",13,13,13,4,1,2,0,0,23 +66,129,0,90000,90,"White",14,NA,NA,6,1,2,0,0,55 +64,190,0,0,0,"White",16,16,16,6,2,2,4,4,45 +64,170,0,57000,57,"White",18,18,18,7,6,2,0,0,47 +68,125,0,15000,15,"White",14,14,14,3,2,2,0,0,21 +71,195,1,13800,13.8,"White",14,14,14,4,1,1,1,1,54 +71,280,1,30000,30,"White",18,18,18,4,2,2,1,1,37 +72,155,1,15000,15,"White",12,12,12,4,3,1,3,3,40 +60,115,0,15000,15,"White",14,14,14,7,1,2,0,0,75 +70,170,1,31000,31,"White",12,12,12,8,7,2,1,1,29 +74,180,1,33000,33,"White",17,17,17,8,7,2,1,1,40 +68,175,1,30000,30,"White",18,18,18,8,1,2,0,0,61 +74,218,1,12000,12,"White",12,12,12,2,1,2,0,0,38 +75,150,1,5000,5,"White",12,12,12,6,1,2,0,0,22 +68,171,1,21000,21,"White",12,12,12,6,6,2,0,0,59 +72,185,1,45000,45,"White",12,12,12,8,7,1,0,0,59 +63,140,0,28000,28,"White",18,18,18,2,4,2,0,0,46 +71,225,1,25000,25,"White",9,9,9,1,1,2,0,0,62 +72,210,1,12000,12,"White",12,12,12,3,2,2,2,2,31 +64,170,0,19000,19,"White",12,12,12,8,2,2,0,0,46 +63,200,0,6000,6,"White",14,14,14,8,1,2,6,6,35 +66,230,0,5300,5.3,"White",13,13,13,1,1,2,0,0,60 +66,121,0,5000,5,"Black",12,12,12,1,1,2,0,0,21 +61,87,0,15000,15,"White",13,13,13,1,4,2,7,7,28 +60,110,1,5000,5,"Black",2,NA,NA,1,1,2,0,0,90 +62,120,0,0,0,"White",12,12,12,2,2,2,3,3,29 +65,145,0,15000,15,"White",11,NA,NA,6,1,1,0,0,59 +73,215,1,17000,17,"White",12,12,12,8,1,2,4,4,46 +66,165,0,4700,4.7,"Black",12,NA,12,5,1,2,6,6,78 +67,139,0,5000,5,"White",12,12,12,8,1,2,0,0,75 +68,113,0,0,0,"White",12,12,12,1,1,2,0,0,18 +62,150,0,9500,9.5,"White",12,12,12,3,1,2,0,0,65 +65,150,1,1700,1.7,"White",12,12,12,8,1,2,1,1,22 +63,130,0,0,0,"White",14,14,14,8,5,2,1,1,43 +62,141,0,5400,5.4,"White",12,12,12,6,1,1,1,1,31 +68,160,1,10000,10,"White",12,12,12,7,2,2,0,0,31 +59,99,0,25000,25,"White",15,15,15,7,1,2,0,0,83 +62,180,0,0,0,"White",12,12,12,6,3,2,2,2,39 +69,165,1,5000,5,"White",13,13,NA,4,2,1,0,0,38 +70,135,0,25000,25,"White",14,14,14,8,4,1,2,2,33 +66,180,1,15000,15,"White",8,8,NA,8,1,2,0,0,82 +64,102,0,0,0,"White",9,9,9,8,1,1,2,2,63 +59,120,0,15000,15,"White",12,NA,NA,1,1,2,0,0,82 +62,100,0,25000,25,"White",10,NA,NA,8,1,1,0,0,73 +68,190,1,30000,30,"White",12,12,12,4,2,2,1,1,42 +68,157,0,35000,35,"White",16,16,16,7,5,2,2,2,43 +63,220,0,25000,25,"White",11,NA,NA,4,1,2,7,7,46 +63,130,0,28000,28,"White",18,18,18,4,2,2,0,0,44 +63,100,0,42000,42,"White",12,12,12,7,1,1,5,5,40 +68,170,1,45000,45,"White",12,12,12,8,1,2,0,0,58 +64,121,0,55000,55,"White",12,12,12,8,7,2,1,1,51 +65,128,0,5000,5,"White",15,15,15,1,5,2,0,0,39 +72,220,1,62000,62,"White",17,17,17,6,1,2,2,2,55 +70,135,0,36000,36,"White",16,16,16,3,2,2,1,1,30 +66,140,0,15000,15,"White",12,12,12,1,1,2,0,0,81 +70,155,1,25000,25,"White",10,NA,NA,8,2,1,0,0,31 +72,220,1,19000,19,"White",12,12,12,6,5,2,0,0,28 +69,165,1,38000,38,"White",11,11,11,4,2,2,0,0,50 +63,120,0,15000,15,"White",14,14,14,8,4,2,1,1,37 +58,114,0,4500,4.5,"White",5,NA,NA,1,1,2,0,0,85 +63,115,0,96000,96,"White",14,14,14,3,7,2,0,0,27 +63,115,0,11000,11,"White",12,12,12,8,1,2,0,0,47 +73,312,1,9000,9,"White",15,15,15,8,2,2,0,0,34 +69,127,0,5000,5,"White",14,14,14,7,7,2,0,0,24 +70,160,1,50000,50,"White",12,12,12,8,1,1,0,0,51 +66,115,0,0,0,"White",12,NA,12,7,1,2,0,0,59 +60,170,0,5000,5,"White",15,15,NA,8,1,2,0,0,56 +66,185,0,0,0,"White",16,16,16,8,1,2,0,0,62 +65,185,0,6000,6,"White",13,13,13,8,1,2,0,0,44 +72,180,1,1e+05,100,"White",13,13,13,6,7,2,7,7,22 +62,130,0,16500,16.5,"White",13,13,13,7,1,2,1,1,46 +72,200,1,25000,25,"White",12,12,12,8,1,2,0,0,54 +69,185,1,0,0,"White",12,12,12,8,7,2,0,0,18 +65,120,0,15000,15,"Black",12,12,12,5,6,2,7,7,32 +73,134,1,15000,15,"Black",14,14,14,2,2,2,0,0,26 +66,140,0,15000,15,"Black",12,12,12,8,5,2,3,3,40 +72,280,1,32000,32,"White",14,14,14,7,1,2,0,0,40 +73,230,1,30000,30,"White",18,18,18,1,1,2,0,0,41 +68,150,0,10000,10,"White",16,16,16,4,1,2,0,0,42 +59,180,0,15000,15,"White",12,12,12,1,1,2,0,0,62 +64,128,0,0,0,"White",12,NA,NA,1,1,1,1,1,35 +66,125,0,15000,15,"White",12,12,12,8,5,2,0,0,19 +60,129,0,6500,6.5,"White",8,8,8,5,1,2,0,0,83 +60,124,0,26000,26,"White",18,18,18,6,5,2,0,0,63 +65,140,0,17000,17,"White",12,12,12,8,3,2,0,0,59 +63,150,0,22000,22,"Other",18,18,18,8,1,2,0,0,59 +64,145,0,10000,10,"White",12,12,NA,8,1,2,0,0,41 +71,165,1,50000,50,"White",14,14,14,8,7,2,0,0,58 +67,162,1,20000,20,"White",12,12,12,6,1,2,0,0,35 +63,145,0,5000,5,"White",12,NA,NA,3,1,2,0,0,67 +67,150,0,0,0,"White",13,13,13,1,7,2,0,0,59 +63,160,0,400,0.4,"White",12,12,12,4,5,1,3,3,31 +72,160,1,30000,30,"White",12,NA,NA,7,1,1,0,0,67 +65,125,0,16000,16,"White",14,14,14,5,1,2,1,1,59 +66,112,0,62000,62,"White",14,14,14,6,2,2,1,1,43 +66,160,0,10000,10,"White",12,NA,NA,3,1,2,0,0,66 +63,115,0,14000,14,"White",13,13,13,4,6,2,0,0,58 +65,112,0,5000,5,"White",15,15,15,3,2,2,5,5,20 +74,210,1,40000,40,"White",16,16,16,5,4,2,0,0,34 +67,170,0,5000,5,"White",13,13,13,8,1,1,2,2,55 +68,185,0,25000,25,"White",17,17,17,1,1,1,0,0,47 +65,150,0,12000,12,"White",12,12,12,2,1,2,1,1,51 +64,137,0,58000,58,"White",16,16,16,4,7,2,5,5,34 +68,128,0,18000,18,"White",16,16,16,4,2,2,1,1,26 +65,147,1,1000,1,"White",12,12,12,7,5,2,0,0,18 +72,265,1,21000,21,"White",17,17,17,6,7,2,1,1,47 +66,158,1,11000,11,"Black",12,12,12,6,4,1,0,0,62 +69,220,1,15000,15,"White",7,7,7,6,1,2,0,0,77 +64,130,0,13000,13,"White",12,12,12,3,1,2,4,4,36 +64,140,0,0,0,"White",12,12,12,8,1,1,0,0,53 +60,110,0,20000,20,"Other",16,16,16,6,1,2,0,0,88 +72,220,1,25000,25,"Black",12,12,12,5,7,1,1,1,35 +70,205,1,5000,5,"Hispanic",8,8,8,7,1,1,0,0,74 +64,130,0,600,0.6,"White",12,12,12,5,1,2,0,0,43 +67,190,1,25000,25,"Black",14,14,14,2,4,2,1,1,26 +69,178,1,15000,15,"White",12,NA,12,8,1,1,1,1,91 +68,140,1,36000,36,"White",12,12,12,2,2,1,0,0,28 +64,175,0,15000,15,"Other",13,NA,13,1,1,2,0,0,33 +64,142,0,35000,35,"White",14,14,14,8,5,2,3,3,36 +66,185,0,3500,3.5,"White",12,12,12,8,1,2,0,0,51 +65,120,0,19005,19.005,"White",16,16,16,1,7,1,1,1,34 +70,170,1,62000,62,"White",14,14,14,1,6,2,0,0,54 +69,195,1,62000,62,"White",16,16,16,7,1,2,0,0,35 +70,135,1,25000,25,"White",12,12,12,8,2,2,1,1,42 +66,180,1,50000,50,"White",12,NA,NA,8,1,2,0,0,52 +64,180,0,0,0,"White",12,12,12,1,1,1,1,1,28 +66,160,0,0,0,"White",13,13,13,5,1,2,0,0,26 +66,140,1,40000,40,"White",12,12,12,8,6,1,0,0,61 +74,190,1,26000,26,"White",18,18,18,2,4,2,1,1,26 +66,132,0,5000,5,"White",12,NA,12,8,1,2,0,0,72 +62,120,0,22000,22,"White",12,12,12,2,2,1,0,0,48 +66,164,0,21000,21,"White",17,17,17,8,1,2,1,1,39 +62,198,0,6108,6.108,"White",12,12,12,1,1,2,0,0,65 +65,145,0,30000,30,"Black",18,18,18,8,4,1,3,3,64 +66,165,0,15000,15,"White",11,NA,11,8,1,2,3,3,68 +64,160,0,15000,15,"White",12,12,12,2,2,2,0,0,79 +63,129,0,6000,6,"White",12,12,12,1,1,2,0,0,78 +66,150,0,15000,15,"White",8,NA,NA,6,1,2,0,0,75 +71,173,1,27000,27,"White",16,16,16,7,1,2,2,2,29 +64,150,0,5000,5,"Hispanic",10,10,NA,2,1,2,0,0,26 +66,160,0,4000,4,"White",16,16,16,7,1,2,7,7,42 +62,165,0,4416,4.416,"Other",6,NA,NA,5,1,2,2,2,72 +66,144,0,5000,5,"White",12,12,12,3,1,1,0,0,39 +64,225,0,5000,5,"Black",9,NA,NA,3,1,1,7,7,62 +67,NA,0,30000,30,"White",16,16,16,8,1,1,0,0,33 +62,130,0,0,0,"White",12,12,12,8,6,2,0,0,76 +63,125,0,5000,5,"White",10,NA,NA,8,1,2,0,0,87 +65,153,0,0,0,"White",9,9,9,1,1,2,0,0,75 +67,175,1,45000,45,"White",18,18,18,1,7,2,0,0,40 +61,130,0,18000,18,"White",14,14,14,5,1,2,3,3,45 +66,125,0,6000,6,"White",15,15,15,8,6,2,0,0,22 +61,155,0,0,0,"White",12,12,NA,7,1,2,1,1,49 +72,200,1,14000,14,"White",12,12,12,4,4,2,0,0,24 +69,125,0,35000,35,"White",14,14,14,1,1,2,7,7,24 +64,120,0,15000,15,"White",16,16,16,8,6,1,0,0,29 +63,126,0,12000,12,"Black",12,12,12,6,3,2,2,2,29 +60,175,0,1000,1,"White",12,NA,NA,5,7,2,7,7,47 +70,195,1,32000,32,"Black",15,15,15,2,2,2,1,1,33 +66,155,0,15000,15,"White",15,15,15,8,3,1,0,0,25 +69,210,1,62000,62,"White",17,17,17,8,7,2,4,4,36 +72,140,1,5000,5,"White",12,12,12,5,6,2,0,0,20 +73,185,1,1500,1.5,"White",12,12,12,8,6,2,1,1,19 +64,130,0,30000,30,"White",12,12,12,8,6,2,0,0,18 +66,138,0,5000,5,"White",13,13,13,8,1,1,0,0,19 +65,150,0,3000,3,"Black",16,16,16,3,1,2,0,0,23 +71,165,1,35000,35,"White",15,15,15,8,2,2,0,0,42 +64,135,0,35000,35,"White",12,12,12,7,5,2,7,7,42 +63,114,0,0,0,"White",12,12,12,4,4,2,0,0,45 +63,132,0,0,0,"White",16,16,16,7,6,2,7,7,29 +72,175,1,70000,70,"White",15,15,15,4,1,1,0,0,48 +67,140,0,21000,21,"White",16,16,16,4,7,2,4,4,28 +69,145,1,50000,50,"White",11,11,11,2,5,2,1,1,18 +71,175,1,15000,15,"White",9,9,9,8,7,1,3,3,21 +68,132,1,0,0,"Hispanic",10,NA,NA,2,2,1,5,5,18 +64,140,0,15000,15,"White",12,NA,NA,1,1,1,0,0,30 +73,172,1,0,0,"Black",12,12,12,5,7,2,2,2,20 +62,142,0,5000,5,"Black",9,NA,NA,8,1,2,7,7,63 +66,150,0,9000,9,"Black",8,8,8,2,1,2,0,0,35 +68,190,1,25000,25,"White",12,12,12,1,1,1,0,0,37 +64,185,0,15000,15,"Black",14,14,14,6,1,2,0,0,63 +63,140,0,10000,10,"Black",14,14,14,8,5,2,1,1,25 +65,125,0,0,0,"White",12,12,12,6,1,1,1,1,60 +66,140,0,5000,5,"Black",18,18,18,6,6,2,1,1,43 +64,126,1,87000,87,"White",12,12,12,8,1,2,1,1,81 +71,175,1,30000,30,"White",12,12,12,4,1,2,0,0,47 +72,185,1,16000,16,"White",14,NA,14,5,7,2,0,0,21 +68,135,1,20000,20,"White",12,12,12,8,2,1,0,0,51 +64,142,0,0,0,"White",12,12,12,2,1,2,0,0,45 +72,185,1,1e+05,100,"White",17,17,17,5,1,2,0,0,54 +72,240,1,62000,62,"White",12,12,12,6,1,2,1,1,69 +66,133,0,10000,10,"White",12,12,12,6,1,2,0,0,43 +72,147,0,62000,62,"White",18,18,18,1,1,2,0,0,35 +66,200,1,35000,35,"White",14,14,14,7,2,2,0,0,63 +65,135,0,7000,7,"White",16,16,16,8,4,2,2,2,31 +65,230,0,0,0,"White",12,12,12,1,1,2,1,1,62 +66,165,0,0,0,"White",12,12,12,1,1,2,0,0,52 +65,230,0,0,0,"White",11,11,NA,2,4,2,7,7,38 +71,180,1,8000,8,"Black",14,14,NA,1,6,2,0,0,27 +74,270,1,11000,11,"White",10,10,10,5,1,1,0,0,50 +70,217,1,25000,25,"White",9,9,NA,8,7,2,1,1,47 +64,130,0,25000,25,"White",14,14,14,4,1,1,0,0,45 +69,175,1,30000,30,"White",14,14,14,1,1,2,1,1,48 +63,120,0,15000,15,"White",12,12,12,1,1,2,7,7,29 +66,130,1,0,0,"White",12,12,12,6,5,2,3,3,26 +63,105,0,48000,48,"White",18,18,18,4,7,1,0,0,34 +68,145,0,17000,17,"White",12,12,NA,2,1,2,0,0,46 +66,180,1,15000,15,"White",12,NA,NA,4,1,2,0,0,69 +78,200,1,25000,25,"White",12,NA,NA,4,2,1,0,0,64 +71,111,0,0,0,"White",8,NA,NA,8,1,2,0,0,70 +73,167,1,26000,26,"White",16,16,16,8,7,2,0,0,24 +69,165,1,25000,25,"White",12,12,12,8,1,2,0,0,32 +63,185,0,10000,10,"White",12,12,12,7,2,2,1,1,61 +62,130,0,25000,25,"White",18,18,18,6,1,1,0,0,50 +65,125,0,0,0,"White",11,11,11,7,1,2,0,0,57 +71,180,1,60000,60,"White",18,18,18,8,5,2,0,0,53 +65,115,0,22000,22,"White",18,18,18,7,5,2,0,0,29 +62,129,0,5000,5,"White",12,12,12,5,6,2,0,0,20 +70,180,1,15000,15,"White",12,12,12,8,1,2,1,1,77 +64,145,0,5000,5,"White",12,12,12,3,7,2,0,0,64 +72,215,1,15000,15,"White",16,16,16,8,1,1,7,7,44 +64,145,0,6200,6.2,"White",13,13,13,5,1,2,0,0,83 +65,132,0,24000,24,"White",16,16,16,2,2,1,7,7,32 +71,143,1,20000,20,"White",14,14,14,8,7,2,2,2,40 +70,150,0,7000,7,"White",14,14,14,6,1,2,0,0,30 +73,155,1,0,0,"Black",12,12,12,1,6,2,1,1,19 +67,115,0,5000,5,"White",15,15,15,4,1,2,1,1,29 +62,121,0,15000,15,"White",12,NA,NA,7,6,1,0,0,60 +68,275,0,30000,30,"Black",16,16,16,8,1,2,3,3,48 +66,130,0,23000,23,"White",18,18,18,8,7,2,3,3,28 +64,130,0,20000,20,"White",12,12,12,2,1,2,0,0,40 +66,170,0,3000,3,"White",16,16,16,8,6,2,1,1,29 +63,135,0,0,0,"White",12,12,12,4,7,2,5,5,31 +70,140,1,30000,30,"White",16,16,16,2,4,2,0,0,41 +64,130,0,12000,12,"White",14,14,14,8,5,2,1,1,23 +66,150,0,35000,35,"White",5,NA,NA,1,1,2,7,7,73 +66,126,0,0,0,"White",7,7,7,8,1,2,4,4,41 +63,140,0,0,0,"White",10,NA,NA,2,1,1,4,4,37 +71,190,1,40000,40,"White",12,12,12,8,4,2,0,0,38 +64,150,0,15000,15,"White",14,14,14,4,1,2,5,5,23 +63,153,0,36000,36,"White",16,16,NA,4,1,2,7,7,45 +66,145,0,10000,10,"White",12,12,12,1,1,1,0,0,53 +63,225,0,0,0,"White",11,NA,NA,4,1,2,0,0,65 +68,120,0,13000,13,"White",14,14,14,7,1,2,0,0,48 +65,265,0,0,0,"White",12,12,NA,1,1,1,7,7,59 +61,120,0,0,0,"White",14,14,14,6,5,2,2,2,41 +62,128,0,10000,10,"Black",12,12,NA,2,1,2,6,6,27 +69,175,1,30000,30,"Hispanic",12,12,12,4,4,2,0,0,37 +69,170,1,5000,5,"White",11,11,11,5,5,2,1,1,18 +65,140,0,25000,25,"White",12,12,12,3,5,2,2,2,33 +64,150,1,23000,23,"White",13,13,13,8,1,1,0,0,32 +70,180,1,20000,20,"White",17,17,17,8,4,2,0,0,68 +65,130,0,19000,19,"White",13,13,13,2,1,2,1,1,82 +68,149,0,62000,62,"White",16,16,16,6,7,2,1,1,60 +61,132,1,20000,20,"Black",11,11,11,7,7,2,0,0,66 +64,180,1,28000,28,"Black",14,14,14,5,7,2,0,0,63 +65,119,0,13000,13,"White",10,10,NA,8,1,2,7,7,80 +64,185,1,12000,12,"White",12,12,12,8,1,2,0,0,75 +63,135,0,25000,25,"White",18,18,18,1,1,2,6,6,36 +69,140,1,20000,20,"White",11,11,11,8,1,2,0,0,23 +66,185,0,15000,15,"White",14,14,14,8,1,2,0,0,62 +61,123,0,15000,15,"White",8,8,8,4,1,2,0,0,78 +74,190,1,25000,25,"White",12,12,12,8,5,1,0,0,30 +68,165,0,25000,25,"White",13,13,13,5,6,2,0,0,52 +68,155,0,0,0,"White",12,12,12,2,7,2,1,1,34 +65,205,0,0,0,"White",14,14,14,4,1,2,2,2,41 +67,132,0,18000,18,"White",16,16,16,7,5,2,7,7,40 +65,115,0,0,0,"White",12,12,12,8,7,1,7,7,18 +64,120,0,0,0,"White",18,18,18,4,1,2,0,0,46 +62,170,0,6000,6,"White",10,10,10,4,1,2,1,1,68 +72,160,1,16000,16,"White",13,13,13,8,6,2,7,7,23 +73,175,1,45000,45,"White",16,16,16,4,1,1,0,0,38 +60,115,0,15000,15,"White",12,12,12,5,7,2,2,2,30 +70,172,1,25000,25,"White",14,14,14,6,1,2,1,1,69 +64,145,0,12000,12,"White",14,14,14,5,2,2,5,5,38 +68,160,0,2000,2,"White",12,12,12,2,5,2,0,0,18 +63,110,0,10000,10,"White",12,12,12,4,6,2,0,0,18 +71,185,1,14000,14,"White",12,12,12,8,1,2,7,7,36 +64,200,0,15000,15,"White",12,12,12,8,1,2,0,0,31 +67,200,0,0,0,"White",11,11,11,8,7,2,0,0,37 +60,140,0,10000,10,"White",12,NA,12,2,1,2,0,0,39 +64,180,0,5000,5,"White",10,NA,NA,1,1,2,0,0,70 +66,157,0,1200,1.2,"White",4,NA,4,3,1,1,4,4,64 +64,155,0,25000,25,"White",12,NA,NA,8,1,2,0,0,74 +59,113,0,15000,15,"White",14,14,14,1,2,2,0,0,62 +63,150,0,10000,10,"White",13,13,13,8,1,2,1,1,64 +66,140,1,2000,2,"White",12,12,12,8,7,2,7,7,18 +66,125,0,0,0,"White",12,12,12,3,2,1,7,7,35 +65,NA,0,4000,4,"White",13,13,13,3,1,1,2,2,33 +70,140,1,5000,5,"White",8,NA,NA,8,1,1,0,0,58 +64,145,0,10000,10,"White",14,14,14,3,2,2,3,3,32 +61,NA,0,5000,5,"White",13,13,13,8,3,1,1,1,22 +66,123,0,15000,15,"White",12,NA,NA,6,1,1,0,0,28 +61,96,0,5000,5,"Hispanic",16,16,16,7,6,2,0,0,22 +66,108,0,1500,1.5,"White",12,12,12,8,1,2,1,1,23 +66,145,1,18000,18,"Hispanic",17,17,17,8,7,2,0,0,26 +73,175,1,4000,4,"White",15,15,15,5,5,2,0,0,24 +72,150,1,28000,28,"White",16,16,16,7,5,2,0,0,26 +74,180,0,10000,10,"White",14,14,14,8,6,2,0,0,22 +65,118,0,3000,3,"White",16,16,16,8,5,2,1,1,22 +64,110,0,0,0,"White",14,14,NA,5,5,2,3,3,31 +62,125,0,25000,25,"White",18,18,18,8,1,2,1,1,68 +71,240,1,12000,12,"White",12,12,12,3,3,2,1,1,21 +62,147,0,15000,15,"White",12,12,12,2,1,2,0,0,77 +68,158,0,19000,19,"White",13,13,13,8,1,1,0,0,45 +61,235,0,0,0,"White",12,12,12,2,1,1,2,2,33 +70,184,1,36000,36,"White",16,16,16,2,1,1,1,1,39 +64,180,0,7000,7,"White",16,16,16,5,6,2,0,0,59 +59,85,0,35000,35,"White",11,11,11,8,4,1,0,0,34 +68,168,1,40000,40,"White",18,18,18,7,1,2,0,0,43 +68,130,1,15000,15,"White",14,14,14,3,1,1,0,0,25 +69,130,0,8000,8,"White",13,13,13,2,1,1,0,0,43 +69,190,0,25000,25,"White",14,14,14,8,1,2,0,0,55 +72,185,1,20000,20,"White",12,12,12,1,7,2,0,0,23 +75,214,1,28000,28,"White",18,18,18,7,6,2,0,0,38 +69,180,1,22000,22,"White",14,14,14,1,4,2,7,7,35 +71,150,1,15000,15,"White",14,14,14,1,5,2,0,0,31 +72,210,1,21500,21.5,"Black",13,13,13,7,7,2,7,7,24 +68,160,0,3000,3,"White",12,12,12,8,2,1,4,4,23 +64,110,0,25000,25,"Other",12,12,NA,8,1,2,2,2,22 +72,190,1,23000,23,"White",13,13,NA,7,4,2,7,7,28 +66,165,0,15000,15,"White",18,18,18,8,4,2,0,0,41 +72,197,1,18000,18,"White",12,12,12,8,1,2,0,0,73 +67,128,1,5000,5,"Hispanic",8,NA,8,8,7,1,0,0,20 +67,156,1,20000,20,"White",16,16,16,8,5,2,0,0,71 +66,150,0,62000,62,"White",14,14,14,8,1,2,1,1,59 +72,164,1,62000,62,"White",14,14,14,7,7,2,0,0,72 +64,120,0,5000,5,"White",13,13,NA,8,1,2,0,0,69 +63,110,0,16000,16,"Hispanic",12,12,12,7,1,2,7,7,46 +69,181,1,15000,15,"White",12,12,12,7,4,1,3,3,26 +63,118,0,53000,53,"Hispanic",17,17,17,4,6,1,0,0,32 +70,200,1,15000,15,"Hispanic",17,17,17,8,1,2,0,0,56 +72,162,1,26000,26,"White",12,NA,12,1,7,2,7,7,27 +70,145,0,20000,20,"White",12,12,12,3,3,1,0,0,33 +65,110,0,4000,4,"Other",12,12,12,7,6,1,1,1,28 +73,200,1,10000,10,"White",16,16,16,8,7,2,1,1,59 +75,220,1,25000,25,"White",12,12,12,8,3,1,0,0,33 +69,230,1,43000,43,"White",12,12,12,2,1,2,0,0,51 +69,180,1,17000,17,"Other",14,14,14,4,4,1,0,0,33 +61,230,0,4000,4,"Hispanic",12,12,12,5,5,2,3,3,38 +71,185,1,87000,87,"White",18,18,18,4,4,2,0,0,55 +72,175,1,30000,30,"Hispanic",13,13,13,8,7,2,5,5,23 +65,135,0,25000,25,"White",16,16,16,6,5,2,7,7,32 +73,195,1,50000,50,"White",15,15,15,8,2,2,7,7,48 +64,123,0,25000,25,"White",18,18,18,8,5,1,0,0,56 +67,137,0,55000,55,"White",18,18,18,8,7,2,3,3,51 +63,145,0,28000,28,"White",16,16,16,4,5,2,5,5,41 +66,160,0,0,0,"White",12,12,12,8,4,2,0,0,48 +72,150,1,15000,15,"White",7,NA,NA,8,1,1,0,0,69 +64,135,0,5000,5,"White",12,12,12,1,4,2,0,0,32 +62,200,0,5000,5,"White",14,14,14,1,1,2,2,2,48 +65,130,0,18000,18,"White",13,13,13,5,1,2,1,1,49 +72,175,1,21000,21,"Hispanic",15,NA,NA,8,7,2,0,0,62 +59,180,0,15000,15,"Hispanic",9,NA,9,6,2,1,4,4,44 +67,115,0,12000,12,"White",12,12,NA,8,1,1,1,1,33 +65,164,0,33000,33,"Hispanic",16,16,16,1,1,2,0,0,62 +64,140,0,15000,15,"White",16,NA,NA,1,1,2,0,0,81 +72,175,1,50000,50,"Hispanic",13,13,13,8,1,1,2,2,64 +65,231,0,6000,6,"Hispanic",9,9,NA,4,1,2,0,0,74 +64,140,0,16000,16,"White",14,14,14,5,6,2,2,2,59 +68,150,1,35000,35,"White",12,12,12,4,6,1,2,2,50 +68,260,0,25000,25,"White",12,12,NA,8,1,2,7,7,43 +66,155,0,35000,35,"White",17,17,17,8,2,2,1,1,41 +76,210,1,20000,20,"White",14,NA,14,8,5,2,0,0,26 +63,118,0,18000,18,"White",12,12,12,7,5,2,3,3,36 +74,225,1,34000,34,"White",14,14,14,3,6,2,0,0,78 +68,155,1,25000,25,"White",16,16,16,7,7,2,0,0,25 +61,110,0,15000,15,"White",14,14,14,1,5,1,0,0,65 +64,140,0,20000,20,"White",16,16,16,2,1,1,0,0,54 +72,200,1,20000,20,"White",17,17,17,8,1,2,0,0,77 +68,170,1,33000,33,"White",12,12,12,7,7,2,0,0,69 +71,150,1,20000,20,"White",12,NA,NA,4,1,2,0,0,66 +63,126,0,15000,15,"White",12,12,12,8,1,2,0,0,76 +65,158,0,4000,4,"White",12,12,12,7,7,2,0,0,73 +60,130,0,20000,20,"White",8,NA,NA,2,1,2,0,0,77 +72,200,1,40000,40,"White",16,16,NA,3,2,1,0,0,33 +64,132,0,14000,14,"White",14,14,14,7,4,1,3,3,40 +68,170,0,12000,12,"White",12,12,12,1,1,1,0,0,48 +61,105,0,25000,25,"White",12,12,12,1,2,2,0,0,31 +63,136,0,10000,10,"White",17,NA,NA,2,1,2,0,0,60 +67,138,0,70000,70,"White",10,NA,NA,8,1,1,0,0,72 +67,140,0,38000,38,"White",17,17,17,5,5,2,7,7,55 +63,125,0,14000,14,"White",12,12,12,5,7,2,5,5,28 +71,164,1,62000,62,"White",18,NA,NA,8,4,2,0,0,76 +63,108,0,0,0,"White",15,15,15,4,3,2,2,2,33 +60,100,0,15000,15,"White",13,13,13,1,7,2,0,0,37 +74,215,1,17000,17,"White",16,16,16,3,1,2,0,0,31 +66,125,0,25000,25,"White",15,15,15,7,6,2,0,0,24 +69,158,1,60000,60,"White",14,14,14,8,2,2,0,0,66 +67,180,0,15000,15,"White",15,NA,15,6,1,2,2,2,69 +65,145,1,25000,25,"White",16,16,16,8,1,2,0,0,86 +62,131,1,18000,18,"Hispanic",12,12,12,8,1,2,0,0,63 +65,145,1,0,0,"White",12,12,12,1,1,2,0,0,55 +64,140,0,45000,45,"White",17,17,17,7,4,2,0,0,54 +72,175,1,70000,70,"White",18,18,18,7,4,1,0,0,47 +66,NA,0,0,0,"Hispanic",11,11,11,7,1,2,4,4,49 +65,130,0,30000,30,"White",18,NA,18,8,1,NA,0,0,59 +67,167,0,1e+05,100,"White",15,15,15,1,1,2,0,0,72 +62,145,0,8000,8,"White",12,12,12,1,1,2,0,0,51 +71,185,1,30000,30,"White",16,16,16,4,6,2,0,0,34 +62,115,0,0,0,"White",11,11,11,6,1,1,7,7,26 +71,192,1,27000,27,"White",14,14,14,5,1,1,0,0,32 +70,270,1,47000,47,"White",18,18,18,8,7,2,1,1,43 +67,135,1,12000,12,"Hispanic",12,12,12,7,7,2,0,0,22 +72,190,1,35000,35,"White",16,16,16,4,2,1,0,0,70 +62,130,0,24000,24,"White",17,17,17,5,1,2,1,1,34 +63,165,0,13000,13,"Hispanic",12,12,12,7,1,2,0,0,35 +61,102,0,80000,80,"White",14,14,14,4,3,1,2,2,37 +72,130,1,5000,5,"White",12,12,12,7,5,2,3,3,18 +65,110,0,0,0,"White",12,12,12,8,6,2,7,7,28 +63,153,0,25000,25,"White",10,10,10,8,6,1,0,0,60 +66,240,1,28000,28,"White",12,12,NA,4,3,2,2,2,44 +64,125,0,8000,8,"White",15,15,15,8,6,2,0,0,20 +66,110,0,10000,10,"White",13,13,13,8,6,1,1,1,51 +68,155,0,9000,9,"White",14,14,14,1,3,2,0,0,41 +60,150,0,20000,20,"White",12,12,12,8,1,2,0,0,37 +65,200,1,12000,12,"White",12,NA,NA,5,1,2,0,0,71 +65,130,0,15000,15,"White",14,14,14,6,1,2,0,0,66 +61,110,0,20000,20,"White",14,14,14,8,7,1,7,7,36 +68,200,0,15000,15,"White",16,16,16,5,2,2,0,0,55 +64,134,0,28000,28,"White",14,14,14,7,6,2,7,7,36 +66,140,0,265,0.265,"White",15,15,15,4,3,2,0,0,21 +69,157,1,35000,35,"White",14,14,14,7,1,2,0,0,74 +67,NA,0,25000,25,"White",12,12,12,5,5,2,0,0,30 +66,165,0,26000,26,"Hispanic",14,14,14,7,1,2,2,2,32 +67,118,0,27000,27,"White",17,17,17,4,1,2,4,4,34 +68,180,0,14000,14,"White",12,12,12,2,2,2,7,7,30 +66,140,1,32000,32,"White",16,16,16,2,3,1,2,2,33 +69,112,0,10000,10,"White",14,14,14,6,1,1,1,1,32 +72,135,1,15000,15,"White",12,12,12,6,1,2,0,0,26 +69,190,1,7000,7,"White",16,16,16,7,5,2,0,0,30 +71,182,1,28000,28,"White",17,17,17,3,4,1,0,0,46 +74,250,1,60000,60,"White",13,13,13,2,1,2,5,5,54 +60,130,0,25000,25,"White",14,14,14,8,1,2,0,0,69 +69,170,1,12000,12,"White",4,4,4,6,1,2,0,0,62 +65,NA,0,0,0,"White",13,13,13,8,1,1,1,1,63 +65,NA,0,0,0,"White",12,12,12,4,2,2,0,0,46 +75,200,0,15000,15,"White",13,13,13,5,1,2,0,0,75 +65,125,0,40000,40,"White",14,14,14,7,1,2,0,0,69 +63,110,0,25000,25,"White",16,16,16,6,1,2,0,0,75 +72,135,1,15000,15,"White",6,NA,NA,7,1,2,0,0,81 +60,112,0,35000,35,"White",12,12,12,1,7,1,7,7,36 +72,225,1,15000,15,"White",11,NA,NA,4,1,1,1,1,63 +64,120,0,26000,26,"White",15,15,15,3,2,2,3,3,32 +59,100,0,0,0,"Black",12,12,12,1,1,1,0,0,43 +71,170,1,0,0,"Other",12,12,12,7,7,2,0,0,20 +72,165,1,26000,26,"Hispanic",16,16,16,8,7,2,0,0,25 +63,108,0,18720,18.72,"Black",10,10,NA,8,1,1,7,7,36 +68,155,0,0,0,"Black",12,12,12,8,6,2,7,7,22 +62,148,0,5000,5,"Other",11,NA,NA,8,1,2,0,0,59 +64,152,0,12000,12,"Black",12,NA,NA,2,1,2,0,0,73 +70,210,1,80000,80,"White",17,17,17,8,3,2,0,0,39 +66,120,0,48000,48,"White",13,13,13,8,6,2,0,0,39 +63,125,0,5000,5,"White",18,18,18,7,6,2,0,0,25 +62,135,1,18000,18,"Other",16,16,16,8,1,2,2,2,27 +70,150,1,85000,85,"White",15,15,15,8,1,2,0,0,65 +64,175,0,35000,35,"Black",12,12,12,1,5,1,2,2,47 +69,150,1,5000,5,"White",16,16,16,8,6,2,0,0,22 +64,140,0,9000,9,"Hispanic",13,13,13,2,4,2,0,0,22 +67,125,0,30000,30,"White",16,16,16,8,6,2,3,3,27 +72,250,1,80000,80,"White",14,14,14,8,1,1,0,0,58 +65,124,0,35000,35,"White",16,16,16,1,7,2,4,4,32 +63,210,0,12000,12,"White",14,14,14,4,1,1,1,1,34 +70,190,1,2e+05,200,"White",18,18,18,6,5,2,7,7,34 +64,128,0,4000,4,"White",16,16,16,6,7,2,0,0,45 +68,165,1,2000,2,"White",12,12,12,1,7,2,1,1,18 +66,190,0,24000,24,"White",18,18,18,3,1,1,0,0,69 +66,165,1,2000,2,"Hispanic",15,15,15,8,5,2,0,0,23 +70,185,1,15000,15,"White",17,17,17,8,4,2,0,0,30 +70,225,1,15000,15,"White",12,12,12,8,1,2,0,0,65 +62,150,0,6000,6,"White",12,12,12,1,1,2,0,0,65 +66,150,1,5000,5,"White",12,12,NA,8,1,2,0,0,75 +66,130,0,1500,1.5,"Hispanic",12,NA,12,5,7,2,7,7,21 +64,130,0,28000,28,"White",18,18,18,5,2,2,0,0,48 +70,150,0,9000,9,"White",12,12,12,8,3,2,0,0,35 +74,175,1,60000,60,"White",14,14,14,7,6,2,0,0,52 +66,150,1,1200,1.2,"White",12,12,12,4,1,2,0,0,19 +62,185,0,1400,1.4,"Hispanic",3,3,3,1,1,2,0,0,64 +68,160,0,15000,15,"White",16,16,NA,8,7,1,0,0,26 +66,180,0,7000,7,"White",13,13,13,1,1,2,0,0,43 +70,190,1,25000,25,"White",12,NA,NA,7,1,2,1,1,72 +62,130,0,21000,21,"White",12,12,12,1,2,2,7,7,31 +69,107,1,44000,44,"White",12,12,12,1,6,2,0,0,58 +68,164,1,29000,29,"Black",16,16,16,8,7,2,0,0,36 +72,165,1,3000,3,"Hispanic",14,14,14,8,1,2,4,4,18 +64,140,1,12000,12,"Black",13,13,13,2,7,2,0,0,22 +64,110,0,0,0,"Hispanic",16,16,16,1,1,2,7,7,19 +60,200,0,0,0,"Hispanic",9,9,9,1,1,2,0,0,39 +72,195,1,20000,20,"Hispanic",12,12,12,8,4,2,0,0,28 +62,146,0,1200,1.2,"Black",5,NA,NA,8,4,2,0,0,73 +64,104,0,25000,25,"White",12,12,12,7,1,1,1,1,30 +74,215,1,37000,37,"White",16,16,16,2,7,2,3,3,25 +66,150,1,8000,8,"Other",10,NA,NA,7,1,2,3,3,60 +68,135,1,35000,35,"Hispanic",16,16,16,8,4,2,3,3,30 +67,145,1,25000,25,"Hispanic",14,14,14,7,7,2,0,0,23 +62,110,1,25000,25,"Other",14,14,14,6,3,2,0,0,37 +71,160,0,18000,18,"White",10,10,10,5,7,2,7,7,29 +63,130,0,30000,30,"Black",16,16,16,8,2,2,4,4,36 +66,133,1,5000,5,"Other",14,14,14,8,7,2,3,3,27 +69,165,1,20000,20,"White",18,18,18,8,6,2,0,0,69 +71,160,1,12000,12,"Hispanic",6,6,6,1,2,2,0,0,40 +64,180,0,0,0,"Hispanic",12,NA,NA,1,7,2,0,0,65 +66,125,0,10000,10,"White",12,12,12,6,1,2,0,0,68 +72,195,1,18000,18,"White",14,NA,NA,8,1,2,2,2,48 +62,115,0,0,0,"Hispanic",15,15,15,8,1,2,0,0,59 +65,130,0,15000,15,"Hispanic",12,12,12,7,7,2,7,7,20 +72,181,1,20000,20,"Black",12,NA,NA,1,1,2,0,0,26 +68,150,0,31000,31,"White",16,16,16,8,7,2,1,1,43 +70,160,1,25000,25,"Black",12,NA,NA,4,2,2,0,0,56 +64,150,1,6000,6,"Hispanic",10,10,10,1,6,1,0,0,36 +64,140,0,0,0,"White",12,12,12,8,7,2,0,0,38 +68,182,1,35000,35,"Black",12,12,12,1,1,1,2,2,70 +70,150,1,12000,12,"White",13,13,13,1,1,2,0,0,40 +66,155,0,13000,13,"White",16,16,16,3,5,2,0,0,33 +67,210,0,26000,26,"White",17,17,17,2,1,2,0,0,34 +68,130,0,15000,15,"Black",11,11,11,2,2,1,7,7,31 +64,140,0,30000,30,"White",17,17,17,4,6,2,0,0,28 +65,122,0,2000,2,"White",14,14,14,8,7,2,0,0,41 +70,150,1,5000,5,"Other",13,13,13,4,2,2,3,3,22 +71,150,0,53000,53,"White",14,14,14,1,1,1,1,1,26 +64,127,0,0,0,"White",12,12,12,8,7,2,3,3,36 +62,102,0,2000,2,"White",13,13,13,1,1,2,7,7,18 +71,155,1,25000,25,"White",17,17,17,2,7,2,1,1,29 +74,185,1,5000,5,"White",12,12,12,8,7,1,0,0,18 +64,105,0,21000,21,"White",13,13,13,4,1,2,1,1,27 +64,NA,0,15000,15,"White",14,14,14,8,1,2,0,0,19 +70,130,0,17000,17,"White",15,15,15,7,6,2,1,1,27 +73,155,1,5000,5,"White",16,16,16,7,7,2,0,0,22 +64,135,0,12000,12,"White",13,13,13,5,2,1,2,2,37 +70,230,1,42000,42,"Hispanic",14,14,14,4,1,2,0,0,44 +74,205,1,21000,21,"White",12,12,12,1,7,2,4,4,33 +63,170,0,6000,6,"Hispanic",12,12,12,8,1,1,0,0,65 +59,107,0,0,0,"Hispanic",12,12,12,2,1,1,5,5,46 +74,190,1,25000,25,"White",14,14,14,1,5,2,0,0,24 +66,119,0,3000,3,"White",14,14,14,6,3,2,0,0,19 +65,150,0,3600,3.6,"White",15,NA,15,7,1,2,0,0,67 +71,155,1,4000,4,"White",12,12,12,8,7,2,4,4,19 +69,160,1,20000,20,"White",14,NA,14,8,5,2,0,0,58 +72,160,1,45000,45,"White",18,18,18,1,4,2,0,0,38 +70,165,1,136500,136.5,"White",16,16,16,6,4,2,0,0,51 +60,220,1,52000,52,"White",15,15,15,4,2,2,0,0,50 +64,130,0,60000,60,"White",12,12,12,4,2,2,1,1,43 +64,122,0,15000,15,"White",13,NA,NA,5,4,2,7,7,41 +72,190,1,90000,90,"White",16,16,16,8,7,2,0,0,50 +63,160,0,35000,35,"White",12,NA,NA,8,1,2,2,2,38 +72,156,1,25000,25,"Hispanic",13,13,13,1,6,1,3,3,19 +66,185,1,15000,15,"White",12,12,12,1,1,2,1,1,76 +61,180,0,26000,26,"White",14,14,14,7,1,2,2,2,65 +62,150,0,0,0,"Hispanic",13,NA,NA,5,1,1,7,7,32 +69,140,1,2000,2,"White",12,12,12,8,7,2,0,0,21 +67,145,0,16000,16,"White",12,NA,12,8,1,2,0,0,61 +65,130,0,24000,24,"Hispanic",11,NA,NA,1,1,2,4,4,27 +68,172,1,15000,15,"Hispanic",16,16,16,4,5,2,0,0,28 +74,170,1,42000,42,"White",17,17,17,8,3,2,0,0,43 +63,150,0,0,0,"White",15,15,15,8,7,1,0,0,48 +65,135,0,10000,10,"White",12,12,12,1,5,1,7,7,43 +71,220,1,17000,17,"Hispanic",13,13,13,7,6,2,0,0,36 +64,NA,0,30000,30,"White",14,14,14,3,2,2,7,7,34 +65,120,0,0,0,"White",16,16,16,5,3,2,2,2,22 +69,160,0,32000,32,"White",17,17,17,2,1,2,0,0,37 +64,135,0,36000,36,"Hispanic",17,17,17,2,7,2,0,0,34 +72,190,1,10000,10,"Hispanic",13,13,13,8,7,2,0,0,20 +63,130,0,20000,20,"White",15,15,15,8,5,2,5,5,29 +65,110,0,24000,24,"White",12,12,12,7,2,2,1,1,29 +72,180,1,17000,17,"White",12,12,12,8,1,1,2,2,32 +65,137,0,23000,23,"White",14,14,14,5,3,2,0,0,48 +64,125,0,25000,25,"White",12,12,NA,4,2,2,2,2,33 +71,200,1,50000,50,"White",12,12,12,4,2,2,0,0,50 +63,145,0,0,0,"White",14,14,14,8,7,2,2,2,39 +62,120,0,20000,20,"White",12,12,12,1,2,2,7,7,30 +66,145,0,30000,30,"White",16,16,16,2,7,2,0,0,33 +64,190,0,7000,7,"White",10,10,10,2,1,1,0,0,39 +67,120,1,7000,7,"White",10,10,10,7,3,2,0,0,78 +68,185,1,30000,30,"White",11,11,11,6,7,2,2,2,32 +66,130,0,3000,3,"White",12,12,NA,1,6,2,0,0,24 +66,145,0,20000,20,"White",14,14,14,8,1,1,0,0,43 +66,139,0,40000,40,"White",16,16,16,7,1,1,0,0,59 +67,150,1,10000,10,"White",12,12,12,7,1,2,0,0,77 +66,240,1,16000,16,"White",12,12,12,8,7,2,0,0,37 +63,225,0,11000,11,"White",9,9,9,3,1,2,2,2,51 +68,175,0,16000,16,"White",13,13,13,2,1,1,3,3,43 +70,185,1,18000,18,"White",12,12,12,4,5,2,0,0,27 +63,115,0,12000,12,"White",16,16,16,8,7,2,0,0,26 +70,170,1,4000,4,"Black",14,14,NA,7,5,1,7,7,21 +72,195,1,60000,60,"White",12,12,12,1,1,1,1,1,45 +75,180,1,43000,43,"White",17,17,17,8,7,2,0,0,40 +62,180,0,31000,31,"White",14,14,14,8,1,2,2,2,39 +68,150,0,50000,50,"White",17,17,17,7,4,2,2,2,39 +68,165,0,27000,27,"White",14,14,14,7,1,2,0,0,29 +70,158,1,30000,30,"White",17,17,17,8,1,2,0,0,56 +73,195,1,12000,12,"Black",13,NA,NA,8,7,2,1,1,21 +66,160,1,136500,136.5,"White",18,18,18,8,7,2,0,0,49 +69,124,0,0,0,"White",16,16,16,1,4,2,4,4,39 +62,140,0,20000,20,"White",17,17,17,7,1,1,2,2,30 +60,120,0,15000,15,"Black",12,12,12,1,1,2,0,0,76 +64,150,0,25000,25,"Other",16,16,16,4,1,1,0,0,37 +68,190,1,5000,5,"Hispanic",12,12,12,1,1,1,4,4,21 +60,125,0,2000,2,"Hispanic",6,NA,NA,8,1,2,0,0,67 +60,140,0,5000,5,"White",14,14,14,8,7,2,0,0,68 +73,170,1,3000,3,"Hispanic",15,15,15,8,6,2,1,1,20 +64,138,0,25000,25,"Black",16,16,NA,2,2,2,1,1,40 +66,130,0,110000,110,"Other",18,18,18,8,1,2,1,1,48 +69,155,1,55000,55,"White",18,18,18,4,1,2,0,0,71 +70,170,1,58000,58,"White",18,18,18,8,1,2,1,1,53 +70,165,0,10000,10,"White",16,16,16,1,6,2,6,6,36 +72,165,1,19000,19,"White",12,12,12,8,2,2,0,0,29 +61,120,0,15000,15,"White",18,18,18,6,1,2,0,0,82 +64,130,0,8000,8,"White",12,12,12,1,1,1,7,7,33 +72,194,1,60000,60,"White",12,12,12,2,1,2,0,0,50 +63,155,0,15000,15,"Other",14,14,14,6,1,2,2,2,69 +68,150,1,6000,6,"White",12,12,12,1,6,1,2,2,27 diff --git a/STAT6101/hibbs.dat b/STAT6101/hibbs.dat new file mode 100644 index 0000000..6d4e92a --- /dev/null +++ b/STAT6101/hibbs.dat @@ -0,0 +1,17 @@ +year growth vote inc_party_candidate other_candidate +1952 2.4 44.6 "Stevenson" "Eisenhower" +1956 2.89 57.76 "Eisenhower" "Stevenson" +1960 .85 49.91 "Nixon" "Kennedy" +1964 4.21 61.34 "Johnson" "Goldwater" +1968 3.02 49.60 "Humphrey" "Nixon" +1972 3.62 61.79 "Nixon" "McGovern" +1976 1.08 48.95 "Ford" "Carter" +1980 -.39 44.70 "Carter" "Reagan" +1984 3.86 59.17 "Reagan" "Mondale" +1988 2.27 53.94 "Bush, Sr." "Dukakis" +1992 .38 46.55 "Bush, Sr." "Clinton" +1996 1.04 54.74 "Clinton" "Dole" +2000 2.36 50.27 "Gore" "Bush, Jr." +2004 1.72 51.24 "Bush, Jr." "Kerry" +2008 .1 46.32 "McCain" "Obama" +2012 .95 52.00 "Obama" "Romney"