The nonparametric counterpart to the randomized block design of the analysis of variance is:
A) Kruskal-Wallis test.
B) Friedman test.
C) Wilcoxon rank sum test.
D) Wilcoxon signed rank test.
E) Sign test for comparing paired samples.

Question

Quizplus · Accepted Answer

The nonparametric counterpart to the randomized block design is the Friedman test, which is used when the dependent variable is ranked or ordinal and there are multiple treatments. The Friedman test is similar to the randomized block design in that it accounts for individual differences between subjects, but it does not assume normality of the data. The Kruskal-Wallis test, Wilcoxon rank sum test, and Wilcoxon signed rank test are all nonparametric tests, but they are not appropriate for analyzing data from a randomized block design. The sign test for comparing paired samples is used when the data is ranked or ordinal and the samples are paired.

The Nonparametric Counterpart to the Randomized Block Design of the Analysis