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).     

Children's abilities and strategies in managing the facial display of affect

To examine children's ability to control their affective expression facially, 68 second- and fourth-grade boys and girls were unobtrusively videotaped while discussing six self-chosen activities about which they felt positively, neutrally, or negatively. Children then performed three facial management tasks: (a)inhibition (showing no emotion instead of a felt emotion); (b)simulation (showing an emotion when not feeling anything); and (c)masking (showing an emotion that is different than what is felt). Twelve raters judged the edited tapes of the children's performance for affect positivity and deceptiveness. Repeated measures ANOVAs indicated, in contrast to previous research, that children were highly competent in managing facial displays. To understand children's techniques for managing affective displays, two raters categorized the primary cognitive strategies children used. Results showed that fourth graders used more complex strategies more often than second graders. These results highlight children's skill and strategies in affect management.Funding for this project was provided by a NICHHD grant (#HD22367) to the first author. We gratefully acknowledge the assistance of Nancy A. Ballard and Michael G. Rakouskas in data collection and preparation. We also thank the children whose participation and cooperation made this research possible.     

Evaluating utility conservation programs: The BPA plan

This paper summarizes a detailed plan for evaluation of the residential energy conservation programs offered by the Bonneville Power Administration (BPA). The major purpose of the evaluation is to determine the energy savings attributable to the programs and to identify differences between program participants and nonparticipants. The focus of this paper is on the sampling issues associated with reliable estimates of energy savings. The methodology attempts to correct for the self-selection bias likely to occur in conservation program evaluation by using intentional nonrandom sampling. In addition, the paper suggests a variety of analytical approaches to analyzing the data with respect to energy savings.The proposed design, using four different groups to estimate program effects, is a comprehensive endeavor. This is appropriate for BPA because of the substantial investment it is making in conservation. However, the design is flexible and allows for use offewer groups to reduce evaluation costs.     

GENDER AND PROSOCIAL VALUES DURING ADOLESCENCE: A Research Note

To date, relatively little is known about the prosocial values of adolescents. Research has shown that females attach more importance to certain prosocial values than males do in late adolescence but has not considered whether this gender difference is evident across stages of adolescence and whether it varies by race. We examine values that focus on doing things for others, using data from a nationwide survey of 12- to 17-year-olds. We find that girls place more importance on these prosocial values than boys at younger ages. However, we also find important patterns in this gender difference across racial groups as well as across age. White boys appear to attach less importance to prosocial values than other race and gender groups. Furthermore, the gender gap in prosocial values is larger at older ages, with older adolescent boys placing less importance on prosocial values than younger ones.     

Using process data to explain outcomes. An illustration from the Child and Adolescent Trial for Cardiovascular Health (CATCH)

The purpose of this article is to illustrate the use of process evaluation for understanding study outcomes. Data from the Child and Adolescent Trial for Cardiovascular Health (CATCH), a large school-based field trial, are used. Teacher characteristics, measures of classroom curriculum implementation, and competing influences are linked to changes in dietary knowledge, intentions, and self-efficacy of students in the intervention schools. Multiple regression analyses indicate that teacher characteristics did not predict program implementation. Teacher characteristics and program fidelity, or the number of modifications made to the classroom curriculum during implementation, had direct and independent effects on student outcomes.     

The MHSIP mental health report card. A consumer-oriented approach to monitoring the quality of mental health plans. Mental Health Statistics Improvement Program

Health care report cards have been endorsed as a mechanism for efficiently comparing key quantifiable aspects of performance across a range of health systems or plans. There are challenges in determining what to measure; how to gather and analyze data; and how to report, interpret, and use findings. Mental health has received little attention, and a consumer perspective is typically not included. The proposed MHSIP mental health report card (MMHRC) addresses these concerns. General issues for report cards are discussed, and the MMHRC is described in terms of content, data sources and quality, and analysis and reporting.     

Fertility Intentions, Career Considerations and Subsequent Births: The Moderating Effects of Women’s Work Hours

Prior research indicates a negative relationship between women’s labor force participation and fertility at the individual level in the United States, but little is known about the reasons for this relationship beyond work hours. We employed discrete event history models using panel data from the National Survey of Families and Households (N = 2,411) and found that the importance of career considerations mediates the work hours/fertility relationship. Further, fertility intentions and the importance of career considerations were more predictive of birth outcomes as women’s work hours increase. Ultimately, our findings challenge the assumption that working more hours is the direct cause for employed women having fewer children and highlight the importance of career and fertility preferences in fertility outcomes.     

The applicability of social control theory in understanding adolescent alcohol use

Utilizing panel data on 345 high school students, this study investigates the efficacy of social control theory in accounting for adolescent orientations toward alcohol use. The findings suggest that the differing informal control mechanisms under consideration place varying constraining influences upon adolescent alcohol use, and upon problems which arise in the lives of adolescents as a consequence of their drinking, throughout the three high, school years. Similarly, alcohol use and its attendant problems are generally found to be associated with a decrease in the strength of adolescents’ bonds to conventionality, though these influences differ in degree from year to year as well.