Semi-Markov Models for Quality of Life Data with Censoring
We present a semi-parametric, semi-Markov, multi-state model for quality of life data measured in continuous time with right censoring. The model is based on the same principles as the Cox proportional hazards model. The states are defined by categorizing a quality of life score as measured using a standard instrument. Death is considered as a separate state in the model. Transitions between the states represent changes in quality of life (or death) and follow a competing risk framework. We describe the model and derive relevant estimators. We illustrate the methodology using data from a cancer clinical trial comparing quality of life for two treatment regimens.
KeywordsSojourn Time Life Data Cancer Clinical Trial Partial Likelihood Markov Renewal Process
Unable to display preview. Download preview PDF.
- Aaronson, N.K., Cull, A.M., Kaasa, S. and Sprangers, M.A.G. (1996). The European Organisation for Research and Treatment of Cancer (EORTC) modular approach to quality of life assessment in oncology: an update. In: Spiker, B. (ed.), Quality of Life and Pharmacoeconomics in Clinical Trials, 2nd Edition. New York: Raven Press, pp. 179–189.Google Scholar
- Andersen, P.K., Borgan, O., Gill, R.D. and Keiding, N. (1992). Statistical Models Based on Counting Processes, New York: Springer-Verlag.Google Scholar
- Cocozza-Thivent, C. (1997). Processus stochastiques et fiabilité des systèmes. Berlin: Springer-Verlag.Google Scholar
- Cox, D.R. (1972). Regression models and life-tables. Journal of the Royal Statistical Society, Series B 34, 269–276.Google Scholar
- Keiding, N., Klein, J.P. and Horowitz, M.M. (2000). Multistate models and outcome prediction in bone marrow transplantation. Research Report 00/1, Department of Biostatistics, University of Copenhagen. Google Scholar
- Kalbfleisch, J.D. and Prentice, R.L. (1980). The Statistical Analysis of Failure Time Data, New York: Wiley.Google Scholar