AN ALTERNATIVE APPROACH FOR MULTIPLE COMPARISON PROBLEMS WHEN THERE ARE A LARGE NUMBER OF GROUPS: ANOM TECHNIQUE

Authors: M. Mende_and S. Yiit
Journal: Journal of Animal and Plant Sciences (JAPS)
ISSN: 1018-7081 (Print), 2309-8694 (Online)
Volume: 28  Issue: 4  Pages: 1074-1079
Year: 2018
DOI: NA
URL: https://doi.org/NA
Publisher: Pakistan Agricultural Scientists Forum

Abstract:
Analysis of Means (ANOM) is a powerful tool for comparing means, variances, proportions and other location and scale measures. This procedure can also be used efficiently as a multiple comparison test especially when there are a large number of groups. A simulation study has been carried out to investigate the performance of ANOM as a multiple comparison approach. Total accuracy value was found at least 60.00% regardless of experimental conditions. ANOM and Tukey procedures have also been compared on a real data set where there are 80 different wheat varieties. It is concluded that the ANOM has a great advantage over Tukey test in terms of determining superior and worse varieties especially when there are more than 10 treatment groups. Garcia et al. (2009) used LSD procedure after ANOVA-F

Keywords: ANOM, multiple comparisons, sensitivity, total accuracy.