SCALE PARAMETER ESTIMATION OF THE LOG-LOGISTIC DISTRIBUTION UNDER THE ASSUMPTION OF SOME SELECTED INFORMATIVE PRIORS
SCALE PARAMETER ESTIMATION OF THE LOG-LOGISTIC DISTRIBUTION UNDER THE ASSUMPTION OF SOME SELECTED INFORMATIVE PRIORS
No Thumbnail Available
Date
2017-01
Authors
DEWU, MUSTAPHA MUHAMMAD
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Log-logistic distribution is a continuous probability distribution that is used in many fields such as hydrology, economics and much more, it has two parameters(scale and shape parameters), in 2015, Nasir et. al. estimated the scale parameter of the distribution using two non-informative priors wherein they concluded that the use of jeffrey’s prior produced better estimate of the scale parameter and on the other hand Precautionary loss function performed better than squared error loss function but their work is limited to the use of non-informative priors only thereby excluding the performance of informative priors when estimating this parameter. Therefore, using the Bayesian estimation technique we estimated the scale parameter of log-logistic distribution using some selected informative priors. Posterior distributions were derived using Gamma, Chi-square, Maxwell and Rayleigh priors under squared error loss function (SELF) and precautionary loss function (PLF). Fairly extensive Monte Carlo simulations were carried out to obtain the Bayes estimates and their corresponding posterior risks after which a performance comparison was carried out on the different priors and loss functions. It was observed that the estimates obtained under the assumption of informative priors outperforms those obtained using non-informative priors and the PLF yields less posterior risk than the SELF. Based on the obtained results, this study recommends the use of Rayleigh prior under PLF for the estimation of the scale parameter of log-logistic distribution.
Description
A DISSERTATION SUBMITTED TO THE SCHOOL OF POSTGRADUATE STUDIES, AHMADU BELLO UNIVERSITY, ZARIA NIGERIA IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE AWARD OF THE DEGREE OF MASTER OF SCIENCE (M.Sc.) IN STATISTICS
Keywords
SCALE PARAMETER ESTIMATION,, LOG-LOGISTIC DISTRIBUTION,, INFORMATIVE PRIORS,, SCALE PARAMETER,