On testing proportionality in the Cox regression model by Andersen's plot |
| |
Authors: | Changyong Feng Hongyue Wang Yun Zhang Yu Han Yuefeng Liang Xin M Tu |
| |
Institution: | 1. Department of Biostatistics and Computational Biology, University of Rochester, Rochester, NY, USA;2. Department of Anesthesiology, University of Rochester, Rochester, NY, USA;3. Department of Statistics, University of California, Davis, CA, USA |
| |
Abstract: | Andersen's plot, a graphical method for testing the proportionality assumption in the Cox Regression Model (Cox, 1972 Cox, D.R. (1972). Regression models and life tables (with discussion). J. Royal Stat. Soc. Ser. B 34:187–220. Google Scholar]), first proposed by Kay (1977 Kay, R. (1977). Proportional hazard regression models and the analysis of censored survival data. Appl. Stat. 26(3):227–237.Crossref] , Google Scholar]) and popularized by Andersen (1982 Andersen, P.K. (1982). Testing goodness of fit of Cox's regression and life model. Biometrics 38:67–77.Crossref], Web of Science ®] , Google Scholar]), has been used widely in biomedical research to check the validity of applying this popular regression model in survival analysis. Our theoretical derivation and examples show that the theoretical basis of this method is flawed. The graphical method should not be used in testing the proportionality. Instead, formal analytical methods based on residuals such as Cox–Snell residual and martingale residual should be used in practice. |
| |
Keywords: | Cox model partial likelihood semiparametric estimation stratification |
|
|