Estimation of a Discriminant Function Based on Small Sample Size from a Mixture of Two Gumbel Distributions
K.E. Ahmad, Zeinhum F. Jaheen, A. A. Modhesh · Communications in Statistics - Simulation and Computation · 2010
The identifiability of finite mixture of Gumbel distributions is proved. A procedure is presented for finding maximum likelihood estimates for the four parameters of a mixture of two Gumbel distributions, using classified and unclassified observations. A nonlinear discriminant function for a mixture of two Gumbel distributions is derived and estimated based on small sample size. Throughout simulation experiments, the performance of the corresponding estimated nonlinear discriminant function is investigated.