Recent literature has emphasized that estimation of duration models sh
ould take account of the sampling scheme generating the data, but this
cannot be done using the duration modules in currently-available pack
ages. This paper shows that discrete-time duration models can be estim
ated easily using widely-available, non-specialist, software packages.
It focuses on the case where the data are for respondents randomly se
lected from a stock at one date and then interviewed after some time i
nterval has elapsed, and also shows that these results generalize to o
ther sampling schemes where the likelihood function requires condition
ing on survival to a data between sample selection and interview. The
findings extend earlier results concerning the easy estimation of dura
tion models which use data from random population samples.