Premium
Sasg × estab: A sas program for computing genotype × environment stability statistics
Author(s) -
Hussein Mohammed Ali,
Bjornstad A ˚ smund,
Aastveit A.H.
Publication year - 2000
Publication title -
agronomy journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.752
H-Index - 131
eISSN - 1435-0645
pISSN - 0002-1962
DOI - 10.2134/agronj2000.923454x
Subject(s) - statistics , mathematics , rank (graph theory) , univariate , stability (learning theory) , nonparametric statistics , linear regression , multivariate statistics , rank correlation , combinatorics , computer science , machine learning
We provide a comprehensive SAS program for the computation of univariate and multivariate stability statistics for balanced data. The program is intended for genotype × location × year (G × L × Y) or genotype × location (G × L) data, averaged over replications (R). It computes the symmetrical joint linear regression with the right and left solutions and Tukey's 1 df for nonadditivity, the regression coefficients ( b ‐ or β‐values), and the deviations from regression (δ ij ) and provides the graphs of the regression lines for both genotypes and locations. Separate regression on the positive and negative sectors of the environmental indices is also conducted. The program calculates Tai's α and λ statistics with graphical presentation of the scatter of the genotypes in the α, λ space. Other outputs of the program include the univariate stability statistics Wricke's ecovalence ( W i 2 ), Shukla's stability variance (σ i 2 ), Hanson's genotypic stability ( D i 2 ), Plaisted and Peterson's θ i , Plaisted's θ ( i ) , Francis and Kannenberg's environmental variance ( S i 2 ), and coefficient of variance (CV); and the rank‐based nonparametric stability statistics S i (2) , S i (3) , S i (6) , Kang's rank sum, and the stratified rank analysis of the genotypes. The program also computes Type 4 stability, superiority measure ( P i ), the desirability index of genotype performance, and the pairwise genotype × environment (G × E) interaction of genotypes with checks. It partitions the G × E interaction into that due to heterogeneity of variances and that due to imperfect correlation between the genotype performance and performs the singular value decomposition of the G × E matrix, plotting the first two interactions’ principal components.