• ASYMPTOTIC PROPERTIES OF THE LOGISTIC AND MULTINOMIAL LOGISTIC REGRESSION MODELS AND ITS APPLICATIONS ON SIMULATION APPROACH

Abstract

Logistic regression is extensively used as a ideal model for the analysis of binary data with the areas of applications including physical, medical and social sciences. In this paper simulation studies are used to estimate the effect of varying sample size, is increases. To assess the accuracy of the estimated parameters and variance components of the logistic and multinomial logistic regression model. As well as the maximum likelihood procedure for the estimation of its parameters are introduced in detail. The essential assumptions are underlying conventional results on the properties of maximum likelihood estimate of the stochastic which determines the behaviour of the observable facts investigated, is known to lie within a specified parameter family of probability distribution. The outcome of the simulation studies are performs we, in performance of the consistency and normality of the Maximum Likelihood Estimation for various sample sizes.