Models for analysing incomplete durations obtained from cross-sectional sur
veys are presented. The aim of the paper is to develop a framework for anal
ysing the incomplete duration of episodes in progress at the time of the su
rvey by formulating generalized linear models and fitting and assessing the
m by using standard statistical packages. The maximum quasi-likelihood meth
od is used for model fitting. The choice of the distribution and the diagno
stic procedures are discussed. Simulated data from two distributions (the W
eibull and log-logistic distributions) are used to evaluate the methodology
developed and to assess model misspecifications. A data set on the current
use of the contraceptive pill from a cross-sectional survey in Egypt is an
alysed.