M. Conde-Amboage, I. Van Keilegom, W. González-Manteiga
Quantile regression allows a more detailed description of the behaviour of the response variable, adapts to situations under more general conditions of the error distribution and enjoys properties of robustness. For all that, quantile regression is a very useful statistical technology for a large diversity of disciplines. In particular, this king of regression provides good results when complex data are considered, for instance, when the response variable is right-censored. Along this talk, a new lack-of-fit test for censored quantile regression models with multiple covariates will be presented.
The test is based on the cumulative sum of residuals with respect to unidimensional linear projections of the covariates. It will be shown the limit distribution of the test statistic and, to approximate the critical values of the test, a wild bootstrap mechanism is used. A simulation study and a real data application will be presented to show the behaviour of the new test in practice.
Keywords: quantile regression, censored data, lack-of-fit test, bootstrap approach, high-dimensional covariates.
Scheduled
GT18 Non-parametric statistics I. Non-parametric hypothesis tests
June 9, 2022 10:10 AM
A15
