The test statistic is:
- and are the means of the two groups being compared and is the mean of the of groups,
- when applying the test to Repeated Measures, each respondent’s average is initially subtracted from their data and it is this corrected data that constitutes of ,
- is the number of observations in the th of groups,
- is the Calibrated Weight for the th observation in the group,
- is the Effective Sample Size for the group,
- for Repeated Measures and otherwise.
- is evaluated using a Tukey’s Studentized Range distribution with degrees of freedom for groups, where is determined by a step down analysis (see Begun, Janet M.; Gabriel, K. Ruben, 1981, "Closure of the Newman-Keuls Multiple Comparisons Procedure", Journal of the American Statistical Association, 76, 241-245).
Circumstances when this test is applied
- Computing either:
- This test has been selected in the Statistical Assumptions setting of Multiple comparison correction > Column comparisons