Mm. Ali et al., Analysis of failure time hierarchical data in the presence of competing risks with application to oral contraceptive pill use in Egypt, STAT MED, 20(23), 2001, pp. 3611-3624
Citations number
26
Categorie Soggetti
Research/Laboratory Medicine & Medical Tecnology","Medical Research General Topics
Problems of practical interest in the analysis of data on contraceptive use
, from Demographic and Health Surveys (DHS), include the estimation of the
cause-specific probability of discontinuation by time t (the cumulative inc
idence function), in the presence of other competing causes and the evaluat
ion of the effect of covariates on the cause-specific hazards of discontinu
ation. Methods of analysis of failure time data with competing risks are by
now fairly well developed in the case of a simple random sample. However,
the data from the DHS are clustered by geographical areas and include multi
ple episodes per woman. For a marginal (population average) approach, we pr
opose using methods developed for simple random samples with standard error
s calculated using a double bootstrap to take account of the clustered hier
archical nature of the data. In the conditional approach, the cause-specifi
c hazards are modelled as log-linear functions of the covariates conditiona
l on random effects of clusters and women, using a three-level multinomial
discrete-time logit model. The methods are applied to data from Egypt 1992
DHS on the oral contraceptive pill use. Copyright (C) 2001 John Wiley & Son
s, Ltd.