Basic Population Synthesis

Abstract

The primary objective of population synthesis can be summarized as generating an individual dataset in full compliance with the statistical characteristics of various input data. Synthetic population is a vital input of the group intelligence study. This chapter reviews algorithms in main streams by distinguishing their data sources. These methods are applied to generating a nationwide synthetic population database of China by using its overall cross-classification tables as well as a 0.95% sample from census. The Synthetic Reconstruction method, published by Wilson in 1976, is the first population synthesis approach. It is most important and extensively used. The central task of this method is composed of two steps: estimating the joint distribution of the target population and realizing the individual dataset. Combinatorial optimization is another sample-based method of population synthesis. It is proposed by Williamson et al. in 1998.