Non-parametric stability measures for analysing non-normal data

Abstract

In the present investigation, five different non-parametric stability measures are proposed based on the ranks of the genotypes to assess genotype-environment interaction, when the data does not satisfy the normality assumption. The behaviours of developed stability indices are studied by simulation technique under the assumption of normal as well as non-normal distributions such as log-normal, gamma, beta and t - distributions. These indices are compared empirically by using power of the test and type-I error. Results from the non-parametric analysis with the help of simulation study demonstrated that the proposed index A4 outperformed other indices in normal as well as nonnormal data scenarios.

Keywords

• Genotype-environment interaction
• Non-parametric measures
• Power of the test
• Stability
• Type-1 error