Title | Checking semiparametric transformation models with censored data. |
Publication Type | Journal Article |
Year of Publication | 2012 |
Authors | Chen, Li, D Y. Lin, and Donglin Zeng |
Journal | Biostatistics |
Volume | 13 |
Issue | 1 |
Pagination | 18-31 |
Date Published | 2012 Jan |
ISSN | 1468-4357 |
Keywords | Biostatistics, Chemotherapy, Adjuvant, Colonic Neoplasms, Granulomatous Disease, Chronic, Humans, Interferon-gamma, Models, Statistical, Monte Carlo Method, Proportional Hazards Models, Survival Analysis |
Abstract | Semiparametric transformation models provide a very general framework for studying the effects of (possibly time-dependent) covariates on survival time and recurrent event times. Assessing the adequacy of these models is an important task because model misspecification affects the validity of inference and the accuracy of prediction. In this paper, we introduce appropriate time-dependent residuals for these models and consider the cumulative sums of the residuals. Under the assumed model, the cumulative sum processes converge weakly to zero-mean Gaussian processes whose distributions can be approximated through Monte Carlo simulation. These results enable one to assess, both graphically and numerically, how unusual the observed residual patterns are in reference to their null distributions. The residual patterns can also be used to determine the nature of model misspecification. Extensive simulation studies demonstrate that the proposed methods perform well in practical situations. Three medical studies are provided for illustrations. |
DOI | 10.1093/biostatistics/kxr017 |
Alternate Journal | Biostatistics |
Original Publication | Checking semiparametric transformation models with censored data. |
PubMed ID | 21785165 |
PubMed Central ID | PMC3276276 |
Grant List | P01 CA142538 / CA / NCI NIH HHS / United States R01 CA082659 / CA / NCI NIH HHS / United States R37 GM047845 / GM / NIGMS NIH HHS / United States R01 CA82659 / CA / NCI NIH HHS / United States |
Checking semiparametric transformation models with censored data.
Project: