Bayesian nonparametric survival analysis for grouped data

A Bayesian nonparametric estimate of the survival distribution is derived under a particular sampling scheme for grouped data that includes the possibility of censoring. The estimate uses the prior information to smooth the data, giving an estimate which is continuous. As special cases survival estimates for life tables are obtained and the estimate of Susarla and Van Ryzin (1976) is derived. As the weight of the prior information tends to zero, the Bayesian estimate reduces to a continuous version of the nonparametric maximum-likelihood estimate. An empirical Bayes modification of the procedure is illustrated on a data set from Cutler and Ederer (1958).     

Public opposition to genetic engineering

Abstract The extent and sources of public opposition to the use of genetic engineering in agricultural production are examined through data from telephone interviews with 220 farmers and 332 nonfarmers living in eight North Carolina counties. A model suggesting that public opposition to genetic engineering is influenced by demographic characteristics mediated by three intervening variables (awareness of genetic engineering, faith in government and industry, and moral objection to genetic engineering) is analyzed. Moral objection is the strongest predictor of opposition. Opposition is also related to lower awareness and less faith in institutions. Women are more likely to oppose genetic engineering than men. Implications of findings are noted.     

Developing alliances between U.S. and Portuguese executives: The impact of executive courage

This study represents an effort to gain insights into the differences between U.S. and Portuguese executives with regard to their attitudes toward the role of executive courage in the business organization. Eighty Portuguese and 40 American executives participated in the study. Four research questions were formulated and investigated. Results show that the two groups of executives tended to be more similar than different. However, some statistically significant differences between the two samples were detected. Portuguese organizations exhibited significantly more control over the actions of their executives and rewarded efficiency rather than effectiveness, when compared to American business organizations. Implications for strategic alliances between Portuguese and American executives are discussed and recommendations for future research are provided.     

Work experience as a source of specification error in earnings models: implications for gender wage decompositions

This paper models the bias from using potential vs actual experience in log wage models. The nature of the problem is best viewed as specification error as opposed to classical errors-in-variables. We correct for the discrepancy between potential and actual work experience and create a predicted measure of work experience. We use the 1979 National Longitudinal Survey of Youth and the Panel Study of Income Dynamics and extend our findings to the Integrated Public Use Microdata Sample. Our results suggest that potential experience biases the effects of schooling and the rates of return to labor market experience. Using such a measure in earnings models underestimates the explained portion of the male–female wage gap. We are able to separately identify the decomposition biases associated with incorrect experience measures and biased parameter estimates.      

Tell It Slant Sex,Disclosure, and HIV

Encounters with HIV can tell us much about how we as individuals communicate about and view our bodies and most intimate selves—how we view and approach truth, lies, sex, and trust. Better ways of handling issues of disclosure in conjunction with changed sexual practices can be crucial to thwarting the HIV pandemic. We interviewed in depth 59 HIV-infected and 18 uninfected gay, bisexual, and heterosexual men and women. Five strategies emerged for dealing with disclosure and safer sex. Clinicians and policymakers need to be as aware and sensitive as possible to the perspectives of men and women grappling with these issues.     

Model Selection and Estimation with Quantal‐Response Data in Benchmark Risk Assessment

This article describes several approaches for estimating the benchmark dose (BMD) in a risk assessment study with quantal dose‐response data and when there are competing model classes for the dose‐response function. Strategies involving a two‐step approach, a model‐averaging approach, a focused‐inference approach, and a nonparametric approach based on a PAVA‐based estimator of the dose‐response function are described and compared. Attention is raised to the perils involved in data “double‐dipping” and the need to adjust for the model‐selection stage in the estimation procedure. Simulation results are presented comparing the performance of five model selectors and eight BMD estimators. An illustration using a real quantal‐response data set from a carcinogenecity study is provided.