COMPARATIVE ANALYSIS OF THE INVERSE WEIBULL DISTRIBUTION BY USING TYPE-II CENSORED SAMPLE
M. ARSLAN NASIR *
Department of Statistics Govt. S.E College, Bahawalpur, Pakistan.
MUSTAPHA MUHAMMAD
Department of Mathematical Science, Bayero University, Kano, Nigeria.
*Author to whom correspondence should be addressed.
Abstract
Parameter estimation become complicated when censoring is present in the sample. Some time it is not possible to give a mathematical expression about estimated values of parameters in Maximum Likelihood (ML) method. In this situation iteration method is used, to find estimated values of parameters in numeric form . There are several Modified Maximum Likelihood (MML) estimation procedures which provide a mathematical expression about parametric value. For the two-parameter inverse Weibull distribution by using type II censored sample, assuming fixed shape parameter, a modified maximum likelihood estimator is proposed by [1] in which they use a simple approximation for intractable terms to estimate the scale parameter. In this paper a comparative study of the proposed estimator [1] is made with MML estimator of [2] ML estimators of [3].
Keywords: Inverse weibull distribution, Type II censored sample, Type II censoring, Modified maximum likelihood estimator, order statistics, Bias, Asymptotic variance, Mean square error