Parameter estimation for the generalized exponential distribution in the presence of interval censored data and covariate

AL-Hakeem, Hussein Ali; Arasan, Jayanthi; Bin Mustafa, Mohd Shafie; Peng, Lim Fong

doi:10.22075/ijnaa.2021.23746.2607

Parameter estimation for the generalized exponential distribution in the presence of interval censored data and covariate

Document Type : Review articles

Authors

Hussein Ali AL-Hakeem ¹

Jayanthi Arasan ²

Mohd Shafie Bin Mustafa ³

Lim Fong Peng ³

¹ Institute for Mathematical Research,43400 UPM Serdang, Selangor, Malaysia

² Department of Mathematics \& Statistics, Faculty of Science, 43400 UPM Serdang, Selangor, Malaysia

³ Department of Mathematics & Statistics, Faculty of Science, 43400 UPM Serdang, Selangor, Malaysia

10.22075/ijnaa.2021.23746.2607

Abstract

This paper concentrates on the parameter estimation for the Generalized Exponential Distribution (GED) in the presence of interval-censored data with covariate. Interval-censored data usually arises in clinical and epidemiological studies. This research attempts to investigate a conservative imputation technique to deal with interval censored data. This is achieved by comparing the bias, standard error (SE) and root mean square error (RMSE) of the maximum likelihood estimation (MLE) obtained without using imputation with the proposed imputation method at various censoring proportion and sample sizes. The results indicate that the proposed imputation method performs better than the traditional method at all sample sizes and censoring proportions.

Keywords

Generalized Exponential distribution

Interval censoring

Covariate

MLE