COMPARISON AND EVALUATION OF DIFFERENT POST-HOC TEST STATISTIC IN ENGINEERING AND EDUCATION USING RANDOMIZED COMPLETE BLOCK DESIGN UNDER ASSUMPTION OF EQUAL VARIANCE.

Abstract

The high percentage of error rate generated by post-hoc test is one of the major challenge of researchers across different fields of enquiry as well as the correct method to adopt, this has lead to under utilization of the numerous methods, this research, aimed at evaluating and comparing various methods to determine the most robust, convenient, optimal and most efficient in  detecting the least percentage comparison wise  and experimental wise error rates under the condition of homogeneity of variance, The research used secondary data from the field of Engineering and Education all in the form of Randomized Complete Block Design, the data were subjected to homogeneity of variance test and the result confirm that their variances were equal (α >0.05),On the same vein the result was able to find out that violation of the assumption for homogeneity of  variance  has no any significant effect on the comparison wise and experimental wise error rates,Similarly the EER generated by the various methods were all less than the alpha level of 10% (<0.10%) ,this  shows that all the methods are best when the researcher is interested in EER, While for the CER, all the methods kept the error rate a little above  ten percent (>10%), except for Tukey and SNK. Therefore, these methods can be adopted in the fields of Engineering and Education depending on the researcher’s interest base on the error type, consequently when the researchers interest is to minimized both comparison and experimental wise error rate, the best methods across the research field is to adopt Tukey  and SNK method as they kept the error rate below the chosen alpha level