Below is the uncorrected machine-read text of this chapter, intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text of each book. Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages.
A VALIDATION EXPERIMENT WITH TRIM2 276 8 A Validation Experiment with TRIM2 Michael L.Cohen, Lynne Billard, David M.Betson, and Eugene P.Ericksen Microsimulation models, of which the Transfer Income Model 2 (TRIM2) is a leading example, as well as other modeling approaches, are currently used to supply the Congress, the executive branch, and others in the policy process with projections of costs and caseloads of tax and transfer programs. Unfortunately, the models are rarely validated. For this reason the Panel to Evaluate Microsimulation Models for Social Welfare Programs decided to conduct, in conjunction with the Urban Institute, an illustrative validation of TRIM2 for a particular federal program, Aid to Families with Dependent Children (AFDC), which we refer to as the âexperiment.â1 Michael Cohen is assistant professor in the School of Public Affairs at the University of Maryland; he served as a consultant to the panel. Lynne Billard, a professor of statistics at the University of Georgia, David Betson, an associate professor of economics at the University of Notre Dame, and Eugene Ericksen, a professor of sociology at Temple University, all served as members of the panel. 1Panel member Lou Gordon was responsible for both the original idea for the experiment and much of the experimental design. Study director Connie Citro was also responsible for much of the experimental design and for coordinating operational issues with staff members of the Urban Institute. Richard Michel, Sheila Zedlewski, Linda Giannarelli, Paul Johnson, and Margaret Moore of the Urban Institute assisted in the experimental design, wrote and modified the required computer software, executed the simulation runs, and documented the results. Joan Turek-Brezina of the Office of the Assistant Secretary for Planning and Evaluation of the U.S. Department of Health and Human Services arranged for funding support from the office, which enabled the panel to make use of the staff and computer resources of the Urban Institute. The data set on which this analysis is based and the unpublished technical memoranda that are cited are available from the Committee on National Statistics. The analysis of the experiment performed by the authors would undoubtedly have benefited if they had had an in-depth understanding of TRIM2. Undoubtedly, such knowledge would have resulted in better insight with respect to which part of the model might be modified to address a discrepancy between the model's estimates and the corresponding observed values. Of course, interaction of persons involved in model validation with those most familiar with the model is essential for model validation, but such interaction was not feasible for our work.