Biometrical Letters vol. 48(2), 2011, pp. 113-121
|
APPLICATION OF STATISTICAL TESTS IN GENE SELECTION PROBLEMS
Joanna Zyprych-Walczak, Alicja Szabelska, Idzi Siatkowski Department of Mathematical and Statistical Methods, Poznan University of Life Sciences, Wojska Polskiego 28, 60-637 Poznań, Poland; e-mail: joanna@up.poznan.pl, aszab@up.poznan.pl, idzi@up.poznan.pl |
Selection of genes is an important issue in discriminant analysis. In this paper we present the use of some statistical tests. Several existing statistical methods such as the F-test, Kruskal-Wallis test for testing the equality of means and Bartlett test, Fligner-Killeen test, and Levene test for testing homogeneity of variance, are presented and compared. These techniques make it possible to find sets of significant genes with different efficiency in relation to discriminant analysis. We present the results obtained based on misclassifications of samples derived with usage of lists of significant genes obtained for the considered tests.
gene, R software, selection, statistical test.
