diff --git a/src/abstractdataframe/abstractdataframe.jl b/src/abstractdataframe/abstractdataframe.jl
index 1d0697debd..df7fd3594e 100644
--- a/src/abstractdataframe/abstractdataframe.jl
+++ b/src/abstractdataframe/abstractdataframe.jl
@@ -374,28 +374,35 @@ end
 Summarize the columns of an AbstractDataFrame
 
 ```julia
-describe(df::AbstractDataFrame)
-describe(io, df::AbstractDataFrame)
+describe(df::AbstractDataFrame; colstats = [:mean, :min, :median, :max, :Nmissing, :datatype])
+describe(io, df::AbstractDataFrame; colstats = [:mean, :min, :median, :max, :Nmissing, :datatype])
 ```
 
 **Arguments**
 
 * `df` : the AbstractDataFrame
 * `io` : optional output descriptor
+* `colstats` a vector of symbols representing the summaristatistics you wish to report
 
 **Result**
 
-* nothing
+* a DataFrame where each row represents a variable of your input DataFrame and each 
+column is a summary statistic
 
 **Details**
 
-If the column's base type derives from Number, compute the minimum, first
-quantile, median, mean, third quantile, and maximum. Missings are filtered and
-reported separately.
+If the column's base type derives from Number, compute the mean, standard 
+deviation, minimum, first quantile, median, third quantile, and maximum. If 
+a column is not numeric, these statistics are populated with `nothing`s. 
 
-For boolean columns, report trues, falses, and missings.
+For variables of *all* types, `describe` can also report the type of the 
+variable and the number of unique values. 
 
-For other types, show column characteristics and number of missings.
+Missings are filtered in the calculation of all statistics, however the optional
+argument `Nmissing` will report the number of missing values of that variable. 
+If the column does not allow missing values, `nothing` is returned. 
+Consequently, `Nmissing = 0` (and not nothing) indicates that the column allows
+missing values, but does not contain any at the time. 
 
 **Examples**
 
@@ -405,10 +412,10 @@ describe(df)
 ```
 
 """
-StatsBase.describe(df::AbstractDataFrame) = describe(stdout, df)
+StatsBase.describe(df::AbstractDataFrame; kwargs...) = describe(stdout, df; kwargs...)
 function StatsBase.describe(io, df::AbstractDataFrame; colstats = [:mean, :min, :median, :max, :Nmissing, :datatype])
     # Check that people don't specify the wrong fields. 
-    allowed_fields = [:mean, :sd, :min, :q25, :median, :q75, :max, :datatype, :NUnique,:Nmissing]
+    allowed_fields = [:mean, :sd, :min, :q25, :median, :q75, :max, :datatype, :Nunique, :Nmissing]
     for i in colstats 
         if !contains(==, allowed_fields, i) 
             error("""
@@ -421,7 +428,7 @@ function StatsBase.describe(io, df::AbstractDataFrame; colstats = [:mean, :min,
                 :max,
                 :datatype,
                 :Nmissing,
-                :NUnique""") 
+                :Nunique""") 
         end
     end
     # Define 4 functions for getting summary statistics 
@@ -438,7 +445,7 @@ function StatsBase.describe(io, df::AbstractDataFrame; colstats = [:mean, :min,
             :max => stats.max,
             :datatype=> eltype(col),
             :Nmissing => nothing,
-            :NUnique => nothing
+            :Nunique => nothing
         )
     end
     
@@ -454,7 +461,7 @@ function StatsBase.describe(io, df::AbstractDataFrame; colstats = [:mean, :min,
             :max => stats.max,
             :datatype=> Missings.T(eltype(col)),
             :Nmissing => count(ismissing(col)),
-            :NUnique => nothing
+            :Nunique => nothing
         )
     end
     
@@ -469,7 +476,7 @@ function StatsBase.describe(io, df::AbstractDataFrame; colstats = [:mean, :min,
             :max => nothing,
             :datatype=> eltype(col),
             :Nmissing => nothing,
-            :NUnique => length(unique(col))
+            :Nunique => length(unique(col))
         )   
     end
     
@@ -484,7 +491,7 @@ function StatsBase.describe(io, df::AbstractDataFrame; colstats = [:mean, :min,
             :max => nothing,
             :datatype=> Missings.T(eltype(col)),
             :Nmissing => count(ismissing(col)),
-            :NUnique => length(unique(col))
+            :Nunique => length(unique(col))
         )    
     end 
     # Takes in a column and returns a row vector of the statistics
diff --git a/test/dataframe.jl b/test/dataframe.jl
index 58d7ec3cf7..b93c4113cc 100644
--- a/test/dataframe.jl
+++ b/test/dataframe.jl
@@ -362,7 +362,10 @@ module TestDataFrame
     
     @test describe(df) == describe_output
 
-    
+    # Test that the keyword arguments works
+    describe_output_mean = describe_output[[:variable, :mean]]
+    @test describe(df, colstats = [:mean]) == describe_output_mean
+
     #Check the output of unstack
     df = DataFrame(Fish = CategoricalArray{Union{String, Missing}}(["Bob", "Bob", "Batman", "Batman"]),
                    Key = CategoricalArray{Union{String, Missing}}(["Mass", "Color", "Mass", "Color"]),