Premium
Some observations on semi‐markov models for partially censored data
Author(s) -
Matthews David E.
Publication year - 1984
Publication title -
canadian journal of statistics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.804
H-Index - 51
eISSN - 1708-945X
pISSN - 0319-5724
DOI - 10.2307/3314748
Subject(s) - hazard , observational study , markov chain , data set , computer science , set (abstract data type) , markov model , econometrics , statistics , data mining , mathematics , artificial intelligence , machine learning , programming language , chemistry , organic chemistry
Cause‐specific hazard functions are employed to analyze a semi‐Markov model which could be used to describe data arising from clinical trials or certain types of observational studies. The use of these hazard functions to fit a set of data arising from N possibly incomplete case histories is shown to have several notable advantages over the approach adopted by Lagakos, Sommer, and Zelen (1978).