Maximum Likelihood Estimation of Parameters for Kumaraswamy Distribution Based on Progressive Type Ii Hybrid Censoring Scheme
Loading...
Date
2023
Authors
Meymuna, Shariff Jaffer
Journal Title
Journal ISSN
Volume Title
Publisher
Kenyatta university
Abstract
The project considers the maximum likelihood estimators for Kumaraswamy distribution based
on progressive type II hybrid censoring scheme using the expectation maximization algorithm. A
two parameter Kumaraswamy distribution can be applied in natural phenomena that have
outcomes with an upper and a lower bound. Kumaraswamy distribution remains of keen
consideration in disciplines such as economics, hydrology and survival analysis. The field of
survival analysis has advanced over the years and extensive research has been undertaken.
Previous studies have considered maximum likelihood estimation for Kumaraswamy distribution
based on progressive type II censoring scheme using methods like Newton-Raphson and EM
algorithm but none has used progressive type II hybrid censoring scheme and obtained maximum
likelihood estimators of Kumaraswamy distribution via EM algorithm. EM algorithm has been
utilized in manipulation of missing data as it is a more superior method when handling
incomplete data. Comparison of different combinations of censoring schemes with respect to the
MSEs and biases at fixed parameters of and are obtained through simulation. It is observed
that in the three censoring schemes, for an increasing sample size, the MSEs and biases are
generally decreasing. Eventually, an illustration with real life data set is provided and it
illustrates how maximum likelihood estimators works in practice under different censoring
schemes.
Description
A Research Project Submitted in Partial Fulfillment of the
Requirements for the Award of the Degree of Master of Science
(Statistics) in the School of Pure and Applied Science of
Kenyatta University
Keywords
Parameters, Kumaraswamy Distribution Based, Type Ii Hybrid Censoring Scheme