# Rankings and Rank Correlations

This package implements various strategies for computing ranks and rank correlations.

`StatsBase.ordinalrank`

— Function`ordinalrank(x; lt = isless, rev::Bool = false)`

Return the ordinal ranking ("1234" ranking) of an array. The `lt`

keyword allows providing a custom "less than" function; use `rev=true`

to reverse the sorting order. All items in `x`

are given distinct, successive ranks based on their position in `sort(x; lt = lt, rev = rev)`

. Missing values are assigned rank `missing`

.

`StatsBase.competerank`

— Function`competerank(x; lt = isless, rev::Bool = false)`

Return the standard competition ranking ("1224" ranking) of an array. The `lt`

keyword allows providing a custom "less than" function; use `rev=true`

to reverse the sorting order. Items that compare equal are given the same rank, then a gap is left in the rankings the size of the number of tied items - 1. Missing values are assigned rank `missing`

.

`StatsBase.denserank`

— Function`denserank(x)`

Return the dense ranking ("1223" ranking) of an array. The `lt`

keyword allows providing a custom "less than" function; use `rev=true`

to reverse the sorting order. Items that compare equal receive the same ranking, and the next subsequent rank is assigned with no gap. Missing values are assigned rank `missing`

.

`StatsBase.tiedrank`

— Function`tiedrank(x)`

Return the tied ranking, also called fractional or "1 2.5 2.5 4" ranking, of an array. The `lt`

keyword allows providing a custom "less than" function; use `rev=true`

to reverse the sorting order. Items that compare equal receive the mean of the rankings they would have been assigned under ordinal ranking. Missing values are assigned rank `missing`

.

`StatsBase.corspearman`

— Function`corspearman(x, y=x)`

Compute Spearman's rank correlation coefficient. If `x`

and `y`

are vectors, the output is a float, otherwise it's a matrix corresponding to the pairwise correlations of the columns of `x`

and `y`

.

`StatsBase.corkendall`

— Function`corkendall(x, y=x)`

Compute Kendall's rank correlation coefficient, τ. `x`

and `y`

must both be either matrices or vectors.