Post hoc analysis of variance test

Abstract

This academic article aimed to present information about how to compare pairs or multiple comparisons (Multiple Comparison), sometimes called Post Hoc Comparison because it is checked after the analysis of variance (ANOVA) with the F test statistic (F-test) when it was found that the average of the overall sample (Omnibus test) was different. Therefore, it must be checked that which pairs of sample means are different? There are many ways to check by comparing pairs. Each method has its own terms. There are different objectives and specific characteristics of comparison. The researcher should consider selecting the comparison method accordingly and appropriate to the nature of the data and the characteristics of the sample group, in order to get the results of the inspection with the least deviation and answer research questions as clearly as possible. Here, the author would like to mention 3 methods of multiple comparison that most researchers like to use to check the differences: LSD method, Tukey-Kramer method, and Scheffe' method. Also, give an example of the steps, analysis methods from the SPSS program using the Scheffe' method, and present the interpretation of the research results.