Friday, October 18, 2002
11:15am
Moos Tower 2-520
Minneapolis Campus
Please note the different day, time, and location than our normally scheduled talks.
Abstract:
Finite population sampling is perhaps the only area of statistics where the primary mode of analysis is based on the randomization distribution, rather than on statistical models for the measured variables. The talk reviews the debate between design and model-based inference. The basic features of the two approaches are illustrated using the question of how to handle selection weights in survey analysis. A modeling strategy based on a mixed effects model for a classification of the sample into "inclusion classes" is described, and applied to a number of survey problems, including stratification, poststratification, PPS sampling and unit nonresponse.
There will be no social tea prior to this talk.
For more details contact 612-624-4655