This article examines the impact of unemployment insurance (UI) on the allocation of labor across industries. An overlooked aspect of UI is the effect of imperfect experience rating on hiring. Firms in more stable industries generally pay more into the UI system than their workers ever receive in benefits, thus subsidizing more volatile industries. The results indicate that industry employment shares are significantly affected by UI and that there is a net shift of resources from the service industry to the construction industry. The estimates also imply that layoff unemployment is increased by about 5% because of UI-induced employment shifts.

An employed worker's search strategies include (1) employed-not searching, (2) employed-searching, and (3) unemployed-searching. The last requires that the worker quit to search. Under plausible assumptions on search costs, the optimal algorithm involves a dual reservation wage strategy (Burdett, 1978). The probability of on-the-job search increases as the current wage decreases relative to the distribution of alternative wages. If the wage is sufficiently low, the searcher quits to search, substituting time for financial outlays. Estimates based on the National Longitudinal Survey of Youth indicate that these calculations characterize the search strategies of young workers. Copyright 1991 by MIT Press.

This paper is concerned with the estimation of covariance matrices in the presence of heteroskedasticity and autocorrelation of unknown forms. Currently available estimators that are designed for this context depend upon the choice of a lag truncation parameter and a weighting scheme. Results in the literature provide a condition on the growth rate of the lag truncation parameter as T → ∞ that is sufficient for consistency. No results are available, however, regarding the choice of lag truncation parameter for a fixed sample size, regarding data-dependent automatic lag truncation parameters, or regarding the choice of weighting scheme. In consequence, available estimators are not entirely operational and the relative merits of the estimators are unknown. This paper addresses these problems. The asymptotic truncated mean squared errors of estimators in a given class are determined and compared. Asymptotically optimal kernel/weighting scheme and bandwidth/lag truncation parameters are obtained using an asymptotic truncated mean squared error criterion. Using these results, data-dependent automatic bandwidth/lag truncation parameters are introduced. The finite sample properties of the estimators are analyzed via Monte Carlo simulation.

This paper establishes the asymptotic normality of series estimators for nonparametric regression models. Gallant's Fourier flexible form estimators, trigonometric series estimators, and polynomial series estimators are prime examples of the estimators covered by the results. The results apply to a wide variety of estimates in the regression model under consideration, including derivatives and integrals of the regression function. The errors in the model may be homoskedastic or heteroskedastic. The paper also considers series estimators for additive interactive regression, semiparametric regression, and semiparametric index regression models, and shows them to be consistent and asymptotically normal. Copyright 1991 by The Econometric Society.

The self-screening properties of initial eligibility determination, a mechanism often under the control of the administrators of targeted transfer programs, are derived and the use of this mechanism in the social security disability insurance system is explored empirically. An increase in the rigor of initial eligibility screening may discourage potential applicants because they are unaware of appeal prospects and because the eligibility decision delay is lengthened, as denied applicants are forced to appeal their claims. In the disability program, a 10 percent increase in the initial denial rate induces a 4 percent decrease in applications. Self-selection is nonperverse.

The positive correlation between schooling and good health is well documented. One explanation is that schooling helps people choose healthier life-styles by improving their knowledge of the relationships between health behaviors and health outcomes. That is, schooling improves the household's allocative efficiency in producing health. This empirical study uses direct measures of health knowledge to test this explanation. Part of the relationship between schooling and the consumption of cigarettes, alcohol, and exercise is explained by differences in health knowledge. However, most of schooling's effects on health behavior remain after differences in knowledge are controlled for. Copyright 1991 by University of Chicago Press.

The positive correlation between schooling and good health is well documented. One explanation is that schooling helps people choose healthier life-styles by improving their knowledge of the relationship between health behaviors and health outcomes. That is, schooling improves the household's allocative efficiency in producing health. This empirical study uses direct measures of health knowledge to test this explanation. Part of the relationship between schooling and the consumption of cigarettes, alcohol, and exercise is explained by differences in health knowledge. However, most of schooling's effects on health behavior remain after differences in knowledge are controlled for.

The self-screening properties of initial eligibility determination, a mechanism often under the control of the administrators of targeted transfer programs, are derived and the use of this mechanism in the social security disability insurance system is explored empirically. An increase in the rigor of initial eligibility screening may discourage potential applicants because they are unaware of appeal prospects and because the eligibility decision delay is lengthened, as denied applicants are forced to appeal their claims. In the disability program, a 10 percent increase in the initial denial rate induces a 4 percent decrease in applications. Self-selection is nonperverse.