EM Algorithm for Type-II Right Censored Bivariate Normal Data

EM algorithm is used to find the maximum likelihood estimates based on Type-II right censored samples from a bivariate normal distribution. The asymptotic variances and covariances of the MLEs are derived, using the missing information principle, from the Fisher information matrix and the partially observed information matrix. Using the asymptotic normality of MLEs and the asymptotic variances and covariances derived, probability coverages of 90% and 95% confidence intervals for all the parameters are evaluated by means of Monte Carlo simulations.