Comparison of algorithms to generate event times conditional on time‐dependent covariates

Statistics in Medicine - Tập 27 Số 14 - Trang 2618-2634 - 2008
Marie‐Pierre Sylvestre1, Michał Abrahamowicz2,3
1Department of Epidemiology and Biostatistics, McGill University, Montreal, QC, Canada
2Department of Epidemiology and Biostatistics, McGill University, 1020 Pine Avenue West, Montreal, Que., Canada H3A 1A2
3McGill University Health Centre, 687 Pine Avenue West, V Building, Montreal, Que., Canada H3A 1A1

Tóm tắt

AbstractThe Cox proportional hazards model with time‐dependent covariates (TDC) is now a part of the standard statistical analysis toolbox in medical research. As new methods involving more complex modeling of time‐dependent variables are developed, simulations could often be used to systematically assess the performance of these models. Yet, generating event times conditional on TDC requires well‐designed and efficient algorithms. We compare two classes of such algorithms: permutational algorithms (PAs) and algorithms based on a binomial model. We also propose a modification of the PA to incorporate a rejection sampler. We performed a simulation study to assess the accuracy, stability, and speed of these algorithms in several scenarios. Both classes of algorithms generated data sets that, once analyzed, provided virtually unbiased estimates with comparable variances. In terms of computational efficiency, the PA with the rejection sampler reduced the time necessary to generate data by more than 50 per cent relative to alternative methods. The PAs also allowed more flexibility in the specification of the marginal distributions of event times and required less calibration. Copyright © 2007 John Wiley & Sons, Ltd.

Từ khóa


Tài liệu tham khảo

Cox DR, 1972, Regression models and life tables (with discussion), Journal of the Royal Statistical Society, Series B, 34, 187

10.7326/0003-4819-145-5-200609050-00009

10.1093/aje/kwi307

10.1001/jama.296.10.1242

10.1001/jama.296.2.185

10.1056/NEJMoa053007

10.1136/bmj.38779.584028.55

10.1146/annurev.publhealth.20.1.145

10.1002/(SICI)1097-0258(19990830)18:16<2123::AID-SIM176>3.0.CO;2-4

10.1016/j.jclinepi.2005.01.021

10.1002/sim.1083

10.1093/biostatistics/4.4.633

10.1016/S0169-2607(97)00043-6

10.2307/2533514

10.1002/sim.2519

10.1002/sim.2400

10.1002/sim.2059

10.1080/01621459.1996.10476711

10.1002/(SICI)1097-0258(19991130)18:22<3075::AID-SIM244>3.0.CO;2-6

10.1002/sim.2673

10.1002/sim.2369

10.1023/A:1020750810409

10.1093/biomet/62.2.269

10.1002/sim.1674

Fishman GS, 2006, A First Course in Monte Carlo

MurrayI. Note on rejection sampling and exact sampling with the metropolised independence sampler. Available from:http://www.gatsby.ucl.ac.uk/∼iam23/pub/04rejection_cftp/rejection_cftp.pdf. (Accessed on 19 January2007).

von Neumann J, 1963, Design of Computer, Theory of Automata and Numerical Analysis, 768

10.1198/016214502753479419

10.1002/sim.2392

R Development Core Team, 2006, R: A Language and Environment for Statistical Computing

10.1145/272991.272995

10.1016/0898-1221(77)90089-X

Thông tin
Thông tin xuất bản

Statistics in Medicine

Tập 27 Số 14

2618-2634

Thông tin tác giả