Generalized Laplacian approximations in Bayesian inference

This paper presents a new Laplacian approximation to the posterior density of η = g(θ). It has a simpler analytical form than that described by Leonard et al. (1989). The approximation derived by Leonard et al. requires a conditional information matrix R_η to be positive definite for every fixed η. However, in many cases, not all R_η are positive definite. In such cases, the computations of their approximations fail, since the approximation cannot be normalized. However, the new approximation may be modified so that the corresponding conditional information matrix can be made positive definite for every fixed η. In addition, a Bayesian procedure for contingency-table model checking is provided. An example of cross-classification between the educational level of a wife and fertility-planning status of couples is used for explanation. Various Laplacian approximations are computed and compared in this example and in an example of public school expenditures in the context of Bayesian analysis of the multiparameter Fisher-Behrens problem.     

The Farm Crisis and Mental Health: A Longitudinal Study of the 1980s1

Abstract This paper examines rural/urban differences and trends in mental health during the farm crisis of the 1980s in a large panel sample from a midwestern state. A community research perspective, which attributes differences to life styles, culture, and community context, is contrasted with an economic stress perspective, which focuses on individual differences in economic circumstances as determinants of rural-urban differences in mental health. Survey samples from 1981, 1986, and 1989 are used to examine differences among seven categories of community type. Multiple regression analysis of the trend and panel data provide support for both the individual economic distress and community context models.     

State minimum wage laws: Youth coverage and impact

Federal minimum wage statutes cover only 70 percent of the work force and 30 percent of all employers. State laws are designed to close some of these coverage gaps and in some cases to set higher wage floors. Hence, differences in state wage floors and coverage should affect employment rates and wage distributions, particularly among low-skilled workers. Evidence from the National Longitudinal Ssurveys of Youth is mixed, however: State wage floors appear to have no impact on youth employment or entry wages, but coverage exemptions appear to increase both employment and wages. These observations underscore the need to include state provisions in models of minimum wage impacts, particularly for later periods (e.g., 1988–1991) when state wage floors were relatively higher.     

Will taxpayers ever like taxes?: Responses to the U.S. Tax Reform Act of 1986

Major policy changes like the 1986 Tax Reform Act (TRA) in the United States provide natural experiments to study attitudinal and behavior responses to law. Surprisingly, public evaluations of the TRA became increasingly negative after passage, while general support for the tax system became more positive in response to the changes. To explain this puzzle, we propose a dynamic model of taxpayer attitudes that is consistent with the observed loose linkage between logically-connected concepts. We briefly review the political context, objectives and impacts of the 1986 Tax Reform Act, and present several studies testing the impact of self-interest, prior beliefs, and social discussion on changes in attitudes and behavior.Results suggest that the complexity of taxes and difficulty in knowing objective impacts weakens the role of self-interest in attitudinal changes, thereby strengthening the role of prior beliefs and discussion. Evaluations of tax laws are most responsive to more politically-oriented influences.     

Evaluation of an educational intervention upon knowledge, attitudes, and behavior concerning drinking/drugged driving.

The Contra Costa County educational program for juveniles found guilty of driving under the influence (DUI) was evaluated. Over 600 juveniles convicted of DUI from 1983 to 1988 formed the study group for this research and of these over 100 participated in the educational program. Assessment of program participants was conducted for knowledge, attitudes and behavior. Participants demonstrated increased knowledge, stronger attitudes against driving under the influence, and less risky alcohol and automobile related behaviors. County juvenile records analyzed by the logit procedure showed that class participants had a significantly lower number of repeat offenses compared to non-program participants that could not be explained by race, offense severity, age or gender.