Nonparametric and semiparametric inferences on the size of an open population.
by Danping Liu
Abstract: Kernel smoothing methods are used to extend the Poisson log linear approach to the estimation of the size of population using multiple lists to an open population when the multiple lists are recorded at each time point. The data is marginal as only the lists at each time point are available and the transitions of individuals between lists at different time points is not observable. When the exogenous variables are available, semiparametric framework is constructed using profile kernel estimating equations to separate the effects of exogenous variables from unexplained trend effects. A simulation study reveals the proposed estimators and their estimated variances give reliable estimates and the resulting approximate confidence intervals have close to their nominal coverage probabilities. The method is applied to data consisting of four lists of drug addicts in Hong Kong from 1977-1997 and several possibly relevant exogenous variables are considered for the parametric part of the model.
For More Information: Owen Jones tel. 8344-6412 email: email@example.com