Modified Cox-Snell Residuals in Evaluating Gompertz Regression Model with Censored Data

In this research, a two parameter Gompertz parametric survival model was extended to incorporate with covariate in the presence of right censored and uncensored data. The estimation procedure was studied at different sample sizes and censoring percentiles via simulation methodology. Statistically, the simulated data were assessed using the bias, standard error and root mean square error of the parameter estimates for the Gompertz regression model. Subsequently, various combinations of sample sizes and censoring levels were employed to evaluate the performance of the proposed modifications to the Cox-Snell residuals for both censored and uncensored observations. The results clearly indicate that the estimates perform well when the censoring degrees are lower, and the sample sizes are greater. The performance of the modified Cox-Snell residuals based on harmonic mean outperformed than the other approaches.