Population Synthesis: Comparing the Major Techniques Using a Small, Complete Population of Firms

Abstract

Recently, disaggregate modeling efforts that rely on microdata have received wide attention by scholars and practitioners. Synthetic population techniques have been devised and are used as a viable alternative to the collection of microdata that normally are inaccessible because of confidentiality concerns or incomplete because of high acquisition costs. The two most widely discussed synthetic techniques are the synthetic reconstruction method (IPFSR), which makes use of iterative proportional fitting (IPF) techniques, and the combinatorial optimization (CO) method. Both methods are described in this article and then evaluated in terms of their ability to recreate a known population of firms, using limited data extracted from the parent population of the firms. Testing a synthetic population against a known population is seldom done, because obtaining an entire population usually is too difficult. The case presented here uses a small, complete population of firms for the City of Hamilton, Ontario, for the year 1990; firm attributes compiled are number of employees, 3‐digit standard industrial classification, and geographic location. Results are summarized for experiments based upon various combinations of sample size and tabulation detail designed to maximize the accuracy of resulting synthetic populations while holding input data costs to a minimum. The output from both methods indicates that increases in sample size and tabulation detail result in higher quality synthetic populations, although the quality of the generated population is more sensitive to increases in tabular detail. Finally, most tests conducted with the created synthetic populations suggest that the CO method is superior to the IPFSR method.

Simulation based population synthesis

“…Openshaw and Rao (1995), Williamson et al (1998), and Voas and Williamson (2000) used Simulated Annealing (SA) as an optimization tool to produce the synthetic population. Ryan et al (2009) compared the CO based methods with the IPF and concluded that CO produced lesser variance. Another advantage is that it has lower memory requirements, though the convergence time of CO based techniques is very high.…”

“…Comparison between IPF and combinatorial optimization based tting can be found in Ryan et al (2009). The experiments here are designed as such that both methods (IPF and simulation based) are provided with the same amount of data about the real population.…”

Transportation infrastructure impacts on firm location: the effect of a new metro line in the suburbs of Madrid

“…Very few studies are available that examine these issues (Baumont et al, 2004;Manzato et al, 2011;Maoh and Kanaroglou, 2007). The studies of Maoh and colleagues (Maoh and Kanaroglou, 2007;Maoh and Kanaroglou, 2009;Maoh et al, 2010;Ryan et al, 2009) for example, were facilitated by access to firm micro-data through a special program with Statistics Canada that allowed the researchers to work at a secure data facility site in Ottawa. This program has since been discontinued, and other suitable databases are typically not easy to access or simply do not exist.…”

Modelling change in supply-chain-structures and its effect on freight transport demand

“…In contrast, the CO approach aims at entropy maximisation by iteratively replacing individuals in a randomly generated population until a bestfit population is found. A comparison of these major techniques regarding the generation of a population of firms has been carried out by Ryan et al (2009) finding general applicability for both methods but recommending CO because of its higher accuracy when synthesising the small benchmark population. A similar study has provided by Klein and Altenburg (2013) who verify the applicability of a Monte Carlo generation procedure for establishments referring to a limited area of northern Germany.…”