Linear discriminant function under multivariate non-normal rice (Oryza sativa) and maize (Zea mays) data

The performance of linear discriminant function was studied under multivariate non-normal situations. The different multivariate non-normal populations were simulated by using the mean vectors and dispersion matrices of rice (Oryza sativa L.) and maize (Zea mays L.) data sets. Further 50 different independent samples were simulated for different dimensions and sample sizes for maize and rice data to obtain empirical probabilities of misclassification. On fitting linear discriminant function to non-normal data the empirical probabilities of misclassification were higher as compared to misclassifying probabilities obtained by using normal approximation. In large sample sizes and in higher dimensions the differences between empirical and normal approximation of probabilities of misclassification were found almost negligible.