Tangent Exponentiated Odd Log-Logistic Weibull Quantile Regression with Applications to Complete and Censored Data | ||||
The Egyptian Statistical Journal | ||||
Volume 69, Issue 1, June 2025, Page 173-205 PDF (1.28 MB) | ||||
Document Type: Original Article | ||||
DOI: 10.21608/esju.2025.359062.1070 | ||||
![]() | ||||
Authors | ||||
Mohammed Hashim Bamba Mustpha ![]() ![]() ![]() ![]() | ||||
1Department of Statistics and Actuarial Science, School of Mathematical Sciences, C. K. Tedam University of Technology and Applied Sciences, Navrongo, Ghana. | ||||
2Department of Biometry, School of Mathematical Sciences, C. K. Tedam University of Technology and Applied Sciences, Navrongo, Ghana. | ||||
Abstract | ||||
A contemporary quantile regression model is formulated utilizing the tan exponentiated odd log-logistic Weibull distribution proposed in this study. The novel regression model is capable of modeling both complete and censored data, making it desirable for survival/reliability analysis. Through reparameterization of the probability density function of the tan exponentiated odd log-logistic Weibull distribution in terms of its quantile function, a suitable quantile regression framework is attained. The estimates of the parameters are attained using the maximum likelihood estimation technique. The findings of the Monte Carlo simulation studies conducted in the study affirm the accuracy of the model under varying levels of censoring and sample sizes. The utilities of the proposed quantile regression model are illustrated by applying it to model gastric cancer and rent datasets, demonstrating superior fit compared to competing models. This work extends the toolkit of quantile regression techniques by proposing a flexible model suitable for handling complete and censored outcomes effectively. | ||||
Keywords | ||||
Quantile regression; GAMLSS; heteroscedasticity; quantile residuals; Weibull distribution | ||||
Statistics Article View: 123 PDF Download: 120 |
||||