The project focuses on two loosely-related hypotheses regarding a contradiction existing in the results of previous research on the relationship between labor force participation and unemployment. This contradiction is the persistent tendency of the estimated effect of unemployment on labor force participation--and hence estimates of "hidden unemployment"--to be greater when cross section data based on Standard Metropolitan Statistical Areas (SMSA) aggregates are used than when economy-wide time series data are used. The hypotheses put forward to explain this contradiction are: (1) that the cross section estimates are biased as the result of labor force heterogeneity across SMSA's; and (2) that the problem of mutual determination of labor force participation and unemployment is a much more likely cause of spurious correlation between these two variables in the cross section than in the time series data. (Author)