Application of multivariate techniques in the evaluation of pure lines of beans

摘要

The objective of this study was to apply multivariate techniques, canonical discriminant analysis, and multivariate contrasts, indicating the most favorable inferences in the evaluation of pure lines of beans. The study was conducted at the experimental field of the Institute for Breeding and Molecular Genetics, in Lages, SC, Brazil. The experiment was composed of 24 pure lines of beans from the Santa Catarina test of cultivars. Plant height, numbers of pods and grains per plant, and stem diameter were the variables measured. The complete randomized block design was used with four replications. The data were subjected to multivariate analysis of variance, canonical discriminant analysis, multivariate contrasts and univariate contrasts. The first canonical discriminant function has captured 81% of the total variation in the data. The Scott-Knott test showed two groups of inbred lines at the average -of scores of the first canonical discriminant function. It was considered that testing hypotheses with the canonical scores may result in loss of information obtained from the original data. Multivariate contrasts indicated differences within the group formed by the Scott-Knott test. The canonical discriminant analysis and multivariate contrasts are excellent techniques to be combined in the multivariate assessment, being used to explore and test hypotheses, respectively.