© 1986 by Biometrika Trust
A note on semi-Markov models for partially censored data
Biometry and Risk Assessment Program, National Institute of Environmental Health Sciences Research Triangle Park, North Carolina 27709, U.S.A.
Department of Biostatistics, Harvard School of Public Health Boston, Massachusetts 02115, U.S.A.
A recharacterization of the semi-Markov model described by Lagakos, Sommer & Zelen (1978) permits the nonparametric maximum likelihood estimators to be expressed in terms of familiar and easily computable quantities, such as event-specific hazard estimators and Kaplan & Meier (1958) survival estimators. In addition to simplifying the calculation and clarifying the interpretation of the previously derived estimators, this reformulation also facilitates the estimation of covariance terms and suggests a simple test of equality among the outcome-specific distributions of sojourn times in a particular state.
Key Words: Event-specific hazard function Kaplan-Meier survival estimator Multistate stochastic process Nonparametric maximum likelihood estimation
![]()
CiteULike
Connotea
Del.icio.us What's this?
This article has been cited by other articles:
![]() |
G. Escarela and J. F. Carriere Fitting competing risks with an assumed copula Statistical Methods in Medical Research, August 1, 2003; 12(4): 333 - 349. [Abstract] [PDF] |
||||
![]() |
J. Gardiner, A. Hogan, M. Holmes-Rovner, D. Rovner, L. Griffith, and J. Kupersmith Confidence Intervals for Cost - Effectiveness Ratios Med Decis Making, August 1, 1995; 15(3): 254 - 263. [Abstract] [PDF] |
||||

