<p>Modeling competing risk data has traditionally relied on exponential and Weibull distributions or their extensions. In this study, we explore an alternative approach by employing the Burr Type XII distribution under Type I censoring. The Burr XII distribution has gained prominence due to its flexibility in capturing diverse data patterns, making it particularly suitable for clinical, biological, and experimental datasets. We derive the Maximum Likelihood Estimators and Bayesian Estimators for the model’s parameters and evaluate their performance through simulation studies and real-world data analysis. Our findings suggest that in the presence of extreme values, heavy-tailed distributions offer a more robust fit compared to classical alternatives. Specifically, while the Weibull distribution remains adequate for datasets with fewer extreme values, the Burr XII distribution emerges as a superior choice when the dataset exhibits a higher concentration of extreme values.</p>