A Rank-Sum Testing Method for Multi-Trait Comprehensive Ranking and Its Application

The rank-sum test is a nonparametric method used in variety evaluation. However, the hypothesis testing of the method hasn't been established for multi-trait comprehensive ranking. In this paper, under null hypothesis H0: the variety's ranking on each trait is random, the theoretical distribution of sum of ranks (SR) was firstly derived and further used to obtain the critical values for multi-trait comprehensive evaluation in rank-sum testing. A new C++ class and its basic arithmetic were defined to deal with the miscount caused by the precision limitation of built-in data type in common statistical software under large number of varieties and traits. Finally, an application of the theoretical results was demonstrated using five starch viscosity traits of 12 glutinous maize varieties. The proposed method is so simple and convenient that it can be easily used to rank different varieties by multiple traits.