rcompanion (version 1.0.1)

pairwiseOrdinalTest: Pairwise two-sample ordinal regression

Description

Performs pairwise two-sample ordinal regression across groups.

Usage

pairwiseOrdinalTest(x, g, method = "fdr", ...)

Arguments

x

The response variable as a vector.

g

The grouping variable as a vector.

method

The p-value adjustment method to use for multiple tests. See p.adjust.

...

Additional arguments passed to clm.

Value

A dataframe of the groups being compared, the p-values, and the adjusted p-values.

Details

Ordinal regression is analogous to general linear regression or generalized linear regression for cases where the dependent variable is an ordinal variable. The ordinal package provides a flexible and powerful implementation of ordinal regression. The pairwiseOrdinalTest function can be used as a post-hoc method following an omnibus ordinal regession whose form is analogous to a one-way analysis of variance. The x variable must be an ordered factor.

References

http://rcompanion.org/handbook/G_07.html

See Also

pairwiseOrdinalMatrix

Examples

data(PoohPiglet)
PoohPiglet$Likert.f = factor(PoohPiglet$Likert, ordered = TRUE)
PoohPiglet = PoohPiglet[order(factor(PoohPiglet$Speaker, 
                        levels=c("Pooh", "Tigger", "Piglet"))),]
pairwiseOrdinalTest(x      = PoohPiglet$Likert.f,
                    g      = PoohPiglet$Speaker,
                    method = "fdr")