Analysis of Yam Yield Data: A Comparison of One –Way Anova and Kruskal -Wallis Test
Year: 2018
Type: article
Abstract: This paper applied the Analysis of Variance Test Statistic on yam data set, to examine the hypothesis that the five plots of yam have identical distributions. It also, examined if any of the basic assumptions of the Analysis of Variance are violated. Secondary data were collected from Otobi Benue State substation of the National Root Crop Research Institute Umudike in Abia State, Nigeria. SPSS software showed that both non-normality and equal variances assumptions were present when Analysis of Variance test statistic was applied. The result from one way analysis of variance (ANOVA) shows that The Fcal = 2.489 < Ftab= 2.76 and the significance of 0.069 is greater than 0.05. The mean= 47.33, standard deviation =19.824 and N = 30, showing that the assumption for normality had been violated in the five plots of yam. This led to the use of Kruskal-Wallis test statistic on the data sets. The Kruskal Wallis result showed that , = ; since .Both test statistics results showed that the five plots of yam have identical distributions. Therefore, the paper concludes that the application of either ANOVA or Kruskal Wallis test when a sample has assumption of ANOVA with homogenous variance but normality is violated leads to the same result.
Author: C. K.
Institution: Michael Okpara University of Agriculture
Language: English
Subfield: Agronomy and Crop Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: diamond
OpenAlex ID: W2991989369