Poststratification provides a systematic approach for improving the precision of sample estimates given prior information on the population distribution. The technique depends upon accurate estimates of the weights (proportions) in each stratum. Applied to two-fold stratification, however, it is often difficult to predict the joint weights without conducting an expensive survey. This report shows how to overcome the estimation problem when marginal totals are known. The resulting model is a nonlinear network (graph); hence, special purpose algorithms are available for solving realistic-size examples. Several modeling extensions and preliminary empirical tests are discussed.
All Science Journal Classification (ASJC) codes
- General Computer Science
- Modeling and Simulation
- Management Science and Operations Research
- Information Systems and Management
- nonlinear programming
- sampling statistics