CMStatistics 2015: Start Registration
View Submission - CMStatistics
B0428
Title: A goodness-of-fit test for the stratified proportional hazards model for survival data Authors:  Jean-Francois Dupuy - INSA de Rennes (France) [presenting]
Rim Ben Elouefi - Monastir University (Tunisia)
Abstract: Goodness-of-fit testing is addressed in the stratified proportional hazards model for survival data. Stratified proportional hazards regression generalizes usual Cox regression by allowing different groups (called strata) of the population under study to have distinct baseline hazard functions. The stratified proportional hazards model has recently been applied in various fields, such as economy, marketing, medicine and public health. Goodness-of-fit testing has thus become a crucial issue in this model. A test statistic based on within-strata cumulative sums of martingale residuals over covariates is proposed. Its asymptotic distribution is derived under the null hypothesis of model adequacy. A Monte Carlo procedure is proposed to approximate the critical value of the test. Simulation studies are conducted to examine finite-sample performance of the proposed statistic for various sample sizes, censoring fractions and numbers of strata. It is shown that the proposed test performs well under a wide range of conditions usually encountered in practice.