The Effect of Censoring Percentages on the Performance of Gamma Distribution in Analysing Survival Data

Abstract

The Gamma distribution was employed to investigate the performance of the model in estimating the maximum likelihood parameter of the model. Simulated data were employed to investigate the performance of the model by considering five different censoring percentages (0%, 10%, 20%, 30% and 40%) and three sets samples of size (100, 300 and 500) observations. The parameters of the Gamma Distribution were estimated successfully. The simulation was repeated 300 times and the mean square error (MSE) and root mean square error (RMSE) were estimated to assess the consistency and stability of the model. The simulated data used to compare the effect of different censoring percentages revealed that the model performed much better with small percentage of censored observations. As the censoring percentage increases the model seems to under estimate the shape parameter and overestimate the scale parameter. The Gamma model showed that survival model is affected by the increase in the percentage of lost information in the data set. However, increasing the sample size helps the model to estimate the parameter of interest much more precise and consistent.