Skip to contents

Pairwise Comparisons

Source: R/pairwise_test.R
pairwise_test.Rd

Pairwise comparisons for Post-hoc testing.

Usage

pairwise_test(
  data,
  x,
  y,
  rowid = NULL,
  type = "auto",
  paired = FALSE,
  var.equal = FALSE,
  trim = 0.2,
  nboot = 100L,
  p.adjust.method = "none",
  alternative = "two.sided",
  conf.level = 0.95,
  internal = FALSE,
  ...
)

Arguments

data

Data frame from which x and y (and possibly rowid if provided) will be searched.

x

Character for the grouping factor. Must be present in data

y

Character for the response variable. Must be present in data.

rowid

Character for the subject-id column. If null, then is assumed that data is sorted for paired designs, creating one. So if your data is not sorted and you leave this argument unspecified, the results can be inaccurate when there are more than two levels in x and there are NAs present.

type

Set "auto" (default) for checking the normality and homogeneity of variances for test selection. Other options are "p" for parametric, "np" for non-parametric and "r" for robust tests.

paired

Logical that decides whether the experimental design is repeated measures/within-subjects or between-subjects. The default is FALSE.

var.equal

Logical variable indicating whether to treat the two variances as being equal. If TRUE then the pooled variance is used to estimate the variance otherwise the Welch (or Satterthwaite) approximation to the degrees of freedom is used.

trim

Trim level for the mean when carrying out robust tests. In case of an error, try reducing the value of tr, which is by default set to 0.2. Lowering the value might help.

nboot

Number of bootstrap samples for computing confidence interval for the effect size (Default: 100L).

p.adjust.method

Adjustment method for p-values for multiple comparisons. Possible methods are: "holm", "hochberg", "hommel", "bonferroni", "BH", "BY", "fdr", "none" (default).

alternative

A character string specifying the alternative hypothesis, must be one of "two.sided" (default), "greater" or "less".

conf.level

Confidence/Credible Interval (CI) level. Default to 0.95 (95%).

internal

Logical to whether this function is being used inside of other functions.

...

Currently ignored.