{"id":109,"date":"2016-09-04T21:58:31","date_gmt":"2016-09-04T21:58:31","guid":{"rendered":"http:\/\/jsr.isrt.ac.bd\/?post_type=article&p=109"},"modified":"2016-09-06T02:17:57","modified_gmt":"2016-09-06T02:17:57","slug":"quantile-regression-models-with-partially-functional-effects-for-randomly-right-censored-data-a-simulation-study","status":"publish","type":"article","link":"http:\/\/jsr.isrt.ac.bd\/article\/quantile-regression-models-with-partially-functional-effects-for-randomly-right-censored-data-a-simulation-study\/","title":{"rendered":"Quantile regression models with partially functional effects for randomly right censored data: A simulation study"},"content":{"rendered":"
Quantile regression presents a flexible approach to the analysis of survival data, allowing\u00a0for modeling quantile-specific covariate effect. Qian and Peng (2010) proposed profile estimating\u00a0equations and a readily and stably implemented iterative algorithm for censored\u00a0quantile regression tailored to the partially functional effect setting with a mixture of varying\u00a0and constant effects and demonstrated improved efficiency of estimation over a naive\u00a0two stage procedure. The aim of this study is to use the same algorithm on a quantile regression\u00a0setting where some covariate effects follow general parametric pattern (e.g. normal,\u00a0gamma or logistic distribution) rather than a constant function or value and to determine the\u00a0strength of using the algorithm in such regression settings through simulation. Simulation\u00a0studies demonstrate that the method works well, for moderately censored data, if the parametric\u00a0pattern g(:) is a known function with unknown parameter(s). A sensitivity analysis\u00a0is performed to check the consequences of misspecification of such parametric pattern.<\/p>\n