stratified_two_sample: Stratified two-sample permutation test for equality of means
In statlab/permuter: permuter: Permutation Tests

Stratified two-sample permutation test for equality of means

1	stratified_two_sample(group, response, stratum, stat = "mean", reps = 1000)

`group`	Vector of group memberships or treatment conditions
`response`	Vector of measured outcomes, same length as group
`stratum`	Vector of stratum assignments, same length as group
`stat`	The test statistic. Default is 'mean'. See details for other options.
`reps`	Number of replications to approximate distribution (default 1000)

If stat == 'mean', the test statistic is (mean(x) - mean(y)) (equivalently, sum(x), since those are monotonically related), omitting NaNs, which therefore can be used to code non-responders
If stat == 't', the test statistic is the two-sample t-statistic– but the p-value is still estimated by the randomization, approximating the permutation distribution. The t-statistic is computed using t.test(...,var.equal=TRUE)
If stat == 'mean_within_strata', the test statistic is the difference in means within each stratum, added across strata.
If stat is a function (a callable object), the test statistic is that function. The function should take a permutation of the pooled data and compute the test function from it.

A vector of length 'reps' containing the permutation distribution

statlab/permuter documentation built on May 30, 2019, 9:45 a.m.