Abstract: | The purchase behaviour of consumers is observed in a panel during a month. The quantity of interest is the penetration of a product. The problem is that this quantity has to be estimated on the basis of incomplete data. For some or all respondents some weeks are missing. To this end the purchasing process is modeled with a variety of stochastic processes. The performance of some existing models is compared for penetrations of the complete population, but also for Bayesian estimates in subpopulations. |