<![CDATA[This study investigates the use of the Modified Inverse Lomax (MILX) distribution to model survival data for patients suffering from Head and Neck cancer who were treated with radiotherapy. The dataset, consisting of 44 observations, is analyzed using maximum likelihood estimation (MLE) and Bayesian methods via Markov Chain Monte Carlo (MCMC) sampling. Key parameters of the MILX model are estimated, and posterior predictive checks are performed to assess model fit. Convergence diagnostics using Gelman-Rubin statistics and trace plots demonstrate reliable parameter estimation, with high effective sample sizes. The model's performance is evaluated using posterior predictive intervals (PPI) and Widely Applicable Information Criterion (WAIC). Residual analysis shows that while the model fits most of the data well, it struggles with larger observed values. The findings highlight the applicability of the MILX distribution in modeling heavy-tailed data with varying uncertainties, and its utility in predicting future observations.]]>
Copyrights © 2025
