Comparing several population means: a parametric bootstrap method, and its comparison with usual ANOVA F test as well as ANOM (Q626256)

A naïve bootstrap technique is considered for hypotheses testing which the authors call CAT (computational approach test). CAT is applied to testing the homogeneity of means hypothesis for multisample data. Its performance is compared to the performance of the standard ANOVA F-test and the analysis of means (ANOM) test. The authors consider data which satisfy a Gaussian one-way ANOVA model, data with Student-t distribution and heteroscedastic data. An example of real life data analysis is also presented.