There are many tourism modelling/forecasting studies, but most of thes
e are concerned with holiday tourism or total tourism (ie not disaggre
gated by visit purpose); conference tourism is virtually ignored. In t
his paper, an econometric model which explains tourism demand for an i
nternational conference is developed. The model is specified in logist
ic form and is estimated using maximum likelihood techniques. Various
alternative forms of the model are considered. For the forecasting mod
el selected, good empirical results are obtained in terms of model fit
, and, in contrast with previous (non-conference) tourism forecasting
findings, the forecasts generated by the econometric model are more ac
curate than random walk forecasts.