Statistical Modelling 5 (2005), 327342
Latent variable models for mixed categorical and
survival responses, with an application to fertility
preferences and family planning in Bangladesh
Irini Moustaki
Department of Statistics,
Athens University of Economics and Business,
76 Patission Street,
GR104 34 Athens,
Greece.
eMail: moustaki@aueb.gr
Fiona Steele
Centre for Multilevel Modelling, Graduate School of Education,
University of Bristol,
Bristol,
UK
Abstract:
In this article, we discuss a latent variable model with
continuous latent variables for manifest
variables that are a mixture of categorical and survival
outcomes. Models for censored and uncensored
survival data are discussed. The model allows for
covariate effects both on the manifest variables (direct
effects) and on the latent variable(s) (indirect effects).
The methodological developments are motivated by
a demographic application: an exploration of women’s
fertility preferences and family planning behaviour
in Bangladesh.
Keywords:
latent variable models; mixed response data;
structural equation modelling; survival analysis
Downloads:
Data in zipped archive
back