Robust Statistics

trim(x; prop=0.0, count=0)

Return a copy of x with either count or proportion prop of the highest and lowest elements removed. To compute the trimmed mean of x use mean(trim(x)); to compute the variance use trimvar(x) (see trimvar).

Example

julia> trim([1,2,3,4,5], prop=0.2)
3-element Array{Int64,1}:
 2
 3
 4

winsor(x; prop=0.0, count=0)

Return a copy of x with either count or proportion prop of the lowest elements of x replaced with the next-lowest, and an equal number of the highest elements replaced with the previous-highest. To compute the Winsorized mean of x use mean(winsor(x)).

Example

julia> winsor([1,2,3,4,5], prop=0.2)
5-element Array{Int64,1}:
 2
 2
 3
 4
 4

trimvar(x; prop=0.0, count=0)

Compute the variance of the trimmed mean of x. This function uses the Winsorized variance, as described in Wilcox (2010).