Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Analysis of censored correlated observations.
AU - Oskrochi, Gholam
PY - 1995/10/1
Y1 - 1995/10/1
N2 - In survival analysis, the most frequently used parametric survival models are the exponential and the Weibull distribution. A random effects model based on a generalized Weibull distribution is proposed for censored correlated observations. The specific individual effects play the role of the random effects part. A conceptually simple and very useful algorithm using the generalized linear model is given, to apply random effects Weibull models to data, and calculate the asymptotic variance-covariance matrix. The model is applied to two real data sets and the results are compared with previous work.
AB - In survival analysis, the most frequently used parametric survival models are the exponential and the Weibull distribution. A random effects model based on a generalized Weibull distribution is proposed for censored correlated observations. The specific individual effects play the role of the random effects part. A conceptually simple and very useful algorithm using the generalized linear model is given, to apply random effects Weibull models to data, and calculate the asymptotic variance-covariance matrix. The model is applied to two real data sets and the results are compared with previous work.
KW - Generalized linear models
KW - Censored data likelihood
KW - Random effect models
KW - EM algorithm
U2 - 10.1016/0378-3758(94)00129-J
DO - 10.1016/0378-3758(94)00129-J
M3 - Journal article
VL - 47
SP - 165
EP - 180
JO - Journal of Statistical Planning and Inference
JF - Journal of Statistical Planning and Inference
SN - 0378-3758
IS - 1-2
ER -