In most empirical work, the investigator's understanding of the economic process under study is only minimally reflected in the econometric methodology. This paper suggests that in many cases, the construction of a small-scale simulation can prepare the data for regression in a manner which takes cognizance of the theory of the process. Regression is then used to scale the output of the simulation up to observed magnitudes of the variable to be predicted. The simulation has the function of exploring for the nature of the nonlinearities and interactions and thus replaces the usual search for a form which maximizes R2. The simulation may also be helpful where colinear data are a problem. An example is presented in which the effects of wages, unemployment rates, and labor turnover on poverty are studied through a prepared regression. IN THE LAST three decades, regression analysis has become the Procrustean bed into which all economic data are fitted. In the usual empirical paper by an economist, the obligatory theoretical discussion which precedes the description of the regressions generally contributes little more to the empirical methodology than an indication of which variables ought to be included in which equation, what the signs of the coefficients might be expected to be, and whether the regressions should be run in linear or logarithmic form. One reaction to this state of affairs has been the commencement of construction of large systems of microsimulation, notably one at the Urban Institute emphasizing demography and the distribution of income [6], one at the National Bureau of Economic Research on urban problems [4], and one at the University of Maryland featuring money flows [2]. While these big microsimulations are designed to describe the processes of the economy in a more natural way than can be done exclusively by usual regression methods, they tend to take years to build and tend to be unavailable to economists not involved in their building. It is possible, however, to occupy a middle ground between the regression runners and the large-model microsimulators. In many cases, improvement over the usual regression procedures can be gained by a combination of a very simple do-it-yourself simulation model with regression. The simulation model has the function of preparing the data for regression, in the sense of exploring for the nonlinearities and variable interactions inherent in the phenomenon under study. The regression, which uses the output of the simulation as an explanatory variable, has the function of scaling the simulation results up to observed magnitudes of the variable under study.

The 1973 Economic Report of the President devotes an entire chapter (ch. 4) to the economic role of women in the United States. In this chapter, the Report recognizes that economic discrimination against women exists and, by the length and thoroughness of the analysis describing its dimensions and consequences, implies that such discrimination constitutes a serious economic (and social) problem. The Report does not attempt to minimize the extent to which job segregation, earnings differentials, higher unemployment rates exist, and the lack of improvement in each component over the last few decades. As economists, we are particularly pleased to have the official imprimatur of an Economic Report on the view that discrimination does indeed exist. Some economists have the tendency to minimize the importance of nonpecuniary forces in influencing decisions made within the firm, and have been reluctant to admit the possibility of discrimination unrelated to real or perceived productivity differences. We believe that a proper analysis of discrimination is yet to come; such an analysis will have to fuse elements of economics, sociology, psychology, and history. Employers do refuse to hire women for certain occupations. Instead they hire men exclusively and pay them more than they would have to pay women of equal ability. The court records are now full of such cases,' but such data will never be explained on the basis of a model which includes in the objective function of the employer only monetary profits. Nor can models which assume that employers' decisions about hiring are based on inborn, unchanging, unexplained tastes do justice to the social forces, both internal and external to the firm, which bear on such decisions. Specifically, it is well known that the average woman college graduate who works full time all year ends up with about the same income as the average male high school dropout. The gross earnings differential works out to be between 35 and 57 percent, depending on the data base used to make the calculation. The Report puts the differential due to discrimination at about 20 percent, but this seems low. In a recent article, Isabel Sawhill reviewed seven econometric studies of male-female earnings patterns. In six of them,2 the differences which could be attributed to discrimination were above 29 percent and ranged up to 43 percent. The seventh study3 estimated the difference which might be attributable to discrimination as 12 percent, but arrived at this figure by classifying as nondiscriminatory the differences in the distribution of men and women among detailed occupations. Since