Quantile Regression Approach to Model Censored Data

Abstract

Abstract

The censored quantile regression model is derived from the censored model. This method is used to overcome problems in modeling censored data as well as to overcome the assumptions of linear models that are not met. The purpose of this study is to compare the results of the analysis of the quantile regression method with the censored quantile regression method for censored data. Both methods were applied to generated data of 150, 500, and 3000 sample size. The best model is then chosen based on the smallest absolute bias and the smallest standard error as an indicator of the goodness of the model. This study proves that the censored quantile regression method tends to produce smaller absolute bias and a smaller standard error than the quantile regression method for all three group data specified. Thus it can be concluded that the censored quantile regression method could result in acceptable model for censored data.

Keywords: Censored data; quantile regression; quantile regression censored; standard error; absolute bias.