Effects of Collinearity on Cox Proportional Hazard Model with Time Dependent Coefficients: A Simulation Study
,
Abstract
Background: The Cox proportional hazard model has gained ground in Biostatistics and other related fields. It has been extended to capture different scenarios, part of which are violation of the proportionality of the hazards, presence of time dependent covariates and also time dependent co-efficients. This paper focuses on the behaviour of the Cox Model in relation to time coefficients in the presence of different levels of collinearity.
Objectives: The objectives of this study are to examine the effects of collinearity on the estimates of time dependent co-effiecients in Cox proportional hazard model and to compare the estimates of the model for the logarithm and the square functions of time.
Materials and methods: The Algorithm based on a binomial model was extended in order to incorporate the different correlation structures required for the study. The scaled Schoenfeld residuals plots revealed the behaviour of the estimated betas at different degrees of collinearity. Results and conclusions are based of outcome of simulation study performed only.
Results: The estimated betas were compared to the true betas at the different level of collinearity in graphical pattern.
Conclusion: The study shows that collinearity is a huge factor that influences the correctness of the estimates of the regressors within the framework of Cox model.
2. Husain H, Thamrin SA, Tahir S, Mukhlisin A, Apriani MM (2018) The application of extended Cox proportional hazard method for estimating survival time of breast cancer. J of Phys [Internet]. 2018; the 2nd International Conference on Science. Conference Series 979 012087. Available from: https://iopscience.iop.org/article/10.1088/17426596/979/1/012087
3. Murphy SA, Sen PK. Time-dependent coefficients in Cox-type regression model. Stoc proc and their applications [Internet]. 1991;39(1):153-180. Available from: https://www.sciencedirect.com/science/article/pi i/030441499190039F
4. Cox DR. Regression models and life-tables (with discussion). J of the Royal Stat Soc, Series B: Methodological [Internet]. 1972; 34(1) 187– 220. Available from: https://www.jstor.org/stable/
5. Salanti G, Ulm K. A non-parametric change point model for stratifying continuous variables under order restrictions and binary outcome. Stat methods in med research[Internet]. (2003); 12(1):351-367. Available from: https://rmgsc.cr.usgs.gov/outgoing/threshold_art icles/Salanti_Ulm2003.pdf
6. Yahya WB, Olaifa JB. A note on Ridge Regression Modeling Techniques. Elect J of App Stat Ana,[Internet]. (2014); 7(2):343-361. Available from: http://sibaese.unisalento.it/index.php/ejasa/article/view/12 502
7. Belsley DA. Assessing the presence of harmful collinearity and other forms of weak data through a test for signal-to-noise. J of Econ [Internet].1980; 20(1): 211-253. Available from: https://link.springer.com/article/10.1007%2FBF 00426854
8. Belsley DA, Kuh E, Welsch RE. Regression Diagnostics. Identifying Influential Data and Sources of Collinearity. New York: John Wiley & Sons.
9. Greene WH. (1993): Econometric Analysis. Englewood Cliffs, NJ: Prentice-Hall.
10. Garba MK, Oyejola BA and Yahya WB. Investigation of Certain Estimators for Modeling Panel Data under Violations of Some Basic Assumptions. Math Theory and Mod [Internet]. 2013 (3)10: 47-53. Available from: https://issuu.com/unilorinbulletin/docs/270114
11. Xue X, Kim MY, Shore RE Cox regression analysis in presence of collinearity: an application to assessment of health risks associated with occupational radiation exposure. Pubmed [Internet]. 2007 Sep; 13(3): 333-350. Available from:
https://www.cdc.gov/niosh/nioshtic2/20040338.html
12. Zhangsheng Y, Xihong L(2010). Semiparametric regression with time-dependent coefficients for failure time data analysis. Statistica Sinica [Internet]. 2010; 20(1); 853-869. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC 2877509/
13. Marzec L, Marzec P. Generalized martingaleresidual processes for goodness-of-fit inference in Cox's type regression models. The ann of stat [Internet]. 1997; 25(2): 683-714. Available from: https://projecteuclid.org/euclid.aos/1031833669
14. Sylvestre MP, Abrahamowicz M. Comparison of algorithms to generate event times conditional on time-dependent covariates. Statist. Med. [Internet]. 2008; 27: 2618–2634. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC 3546387/
15. Vatcheva KP, Lee M, McCormick JB, Rahbar MH. Multicollinearity in Regression Analyses Conducted in Epidemiologic Studies. Epidemiol [Internet]. 2016 Apr; 6(2):227-232.Available from: https://www.ncbi.nlm.nih.gov/pubmed/2727491 1
16. Mai Z. (2003). Understanding Cox regression models with time-change covariates, University Kentucky Print, 2003; 1-9. Available from: http://www.ms.uky.edu/~mai/research/amst.pdf
17. Teresa MP, Melissa EB. (2012). Your “Survival” Guide to Using Time ‐Dependent Covariates. SAS Global forum, 2012; 168-178. Available from: https://support.sas.com/resources/papers/proceed ings12/168-2012.pdf
18. Fleming TR, Harrington DP. (1991). Counting Processes and Survival Analysis. John Wiley & Sons.
| Files | ||
| Issue | Vol 5 No 2 (2019) | |
| Section | Original Article(s) | |
| DOI | https://doi.org/10.18502/jbe.v5i2.2348 | |
| Keywords | ||
| Baseline hazard Time-dependent coefficien Collinearity Schoenfeld residual | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
