Mathematical and Computer Modelling: An International Journal
Nonparametric Bayes error estimation using unclassified samples
IEEE Transactions on Information Theory
Variance comparisons for unbiased estimators of probability of correct classification (Corresp.)
IEEE Transactions on Information Theory
Hi-index | 0.98 |
A procedure is presented for finding maximum likelihood estimates of the parameters of a mixture of two Weibull distributions. Estimation of a nonlinear discriminant function on the basis of small sample size is considered. Throughout simulation experiments, the total probabilities of misclassification and percentage biases are evaluated and discussed. The problem of updating a nonlinear discriminant function on the basis of two Weibull distributions is studied in situations when the additional observations are mixed or classified. The performance of all results is investigated using a series of simulation experiments by means of relative efficiencies.