Noninformative priors for the common mean in the bivariate normal distribution

In this paper, we consider some noninformative priors for the common mean in a bivariate normal population. We develop the first-order and second-order matching priors and reference priors. We find that the second-order matching prior is also an HPD matching prior, and matches the alternative coverage probabilities up to the second order. It turns out that derived reference priors do not satisfy a second-order matching criterion. Our simulation study indicates that the second-order matching prior performs better than the reference priors in terms of matching the target coverage probabilities in a frequentist sense. We also illustrate our results using real data.     

On estimating the distribution of data envelopment analysis efficiency scores: an application to nursing homes’ care planning process

Data envelopment analysis (DEA) is a deterministic econometric model for calculating efficiency by using data from an observed set of decision-making units (DMUs). We propose a method for calculating the distribution of efficiency scores. Our framework relies on estimating data from an unobserved set of DMUs. The model provides posterior predictive data for the unobserved DMUs to augment the frontier in the DEA that provides a posterior predictive distribution for the efficiency scores. We explore the method on a multiple-input and multiple-output DEA model. The data for the example are from a comprehensive examination of how nursing homes complete a standardized mandatory assessment of residents.     

Consistency of minimizing a penalized density power divergence estimator for mixing distribution

In this paper, we study the MDPDE (minimizing a density power divergence estimator), proposed by Basu et al. (Biometrika 85:549–559, 1998), for mixing distributions whose component densities are members of some known parametric family. As with the ordinary MDPDE, we also consider a penalized version of the estimator, and show that they are consistent in the sense of weak convergence. A simulation result is provided to illustrate the robustness. Finally, we apply the penalized method to analyzing the red blood cell SLC data presented in Roeder (J Am Stat Assoc 89:487–495, 1994). This research was supported (in part) by KOSEF through Statistical Research Center for Complex Systems at Seoul National University.     

A Model of Quality of College Life (QCL) of Students in Korea

This study develops and tests a model of quality of college life (QCL) of students in Korea. In this study, QCL of students is conceptualized in terms of needs satisfaction and affect balance. It has been hypothesized that satisfaction with education services, administrative services, and facilities have a significant impact on QCL, which in turn positively influences identification, positive word of mouth, and overall quality of life. The results of a survey on 228 Korean college students largely support the model. Managerial and policy implications are discussed.     

A longitudinal analysis of the impact of health shocks on the wealth of elders

We investigate the impact of health shocks on wealth, using all four waves of the Health and Retirement Study, and estimate not only the short-term effect but also the long-term effect of health shocks on wealth of the elderly. We find that new health events lower wealth in elders during the period in which such health shocks occur, but the impact tends to disappear over time. We also find that health shocks result in greater wealth depletion when they occur later in life. Together with existing health problems, the overall impact of health problems on wealth increases over time.

Cleaning Up Water? Or Building Rural Community? Community Watershed Organizations in Pennsylvania*

Abstract Recent initiatives from state and federal government agencies have helped foster the formation of community‐based watershed organizations. Although there is a great deal of enthusiasm about the potential of these organizations to enhance water quality, relatively little attention has been paid to the impacts these organizations may have on the well‐being of rural communities more generally. Assessments of effectiveness have typically focused on specific activities and accomplishments, rather than a broader range of community‐based effects. In short, we ask whether community‐based environmental management improves community as well as environment. Our research utilized a mixed‐methods design, including a statewide mail survey of all Pennsylvania watershed organizations, followed by in‐depth interviews with 28 rural watershed organizations. This sequential approach progressively explored in more detail definitions of effectiveness, including the building of rural capacity. We find watershed organizations are potentially effective mechanisms for building local leadership, enhancing the skills of rural residents, and making valuable connections with other communities, facing similar water‐resource and rural‐development issues. However, the range of issues with which local watershed organizations engage and the methods they currently utilize may eventually limit their usefulness.     

Competition for Resources: A Reexamination of Sibship Composition Models of Parental Investment

The predictions of resource dilution and sibship gender composition models of educational investment are tested using the Japanese Nationwide Survey on Families (N = 6,985). Japan is an important case because of its postindustrial economy, coupled with high levels of dependence on parental investment to attend a university and persisting gender inequality in educational attainment. In previous between‐family analyses of educational attainment in Japan, boys were found to drain resources from their sisters. The within‐family, multilevel models of parental educational investments in this analysis show that girls with college‐educated brothers fare better than their peers without brothers. An alternative model incorporating the educational investments received by brothers in the same family is proposed.     

The NIP graph of a social welfare function

We consider the fraction of pairs of m distinct alternatives on which a social welfare function f may be nondictatorially independent and Pareto when the domain of f satisfies the free k-tuple property. When k = 4 we improve the existing upper bound to . When there are at least 26 alternatives and we obtain an original upper bound, . To obtain these results we define and analyze the graph formed from the nondictatorial independent and Pareto pairs and combine the results of this analysis with known results from extremal graph theory. The authors extend special thanks to the two reviewers and the editor for their comments.     

Origins of the epithet ‘government by public relations’: Revisiting Bruce Catton's War Lords of Washington, 1948

While it might make public relations professionals and faculty cringe, the term ‘government by public relations’ is a negative one, implying that governmental decision-making is guided by appearances rather than on the merits. This tag line is a relatively common American put-down of politicians and senior civil servants. This article examines the origins of the term, locating its usage in the WWII memoirs of Bruce Catton, then a government public information officer and later a renowned popular historian of the American Civil War. Catton's use of the term, his 1948 book War Lords of Washington, and his philosophy of government public information are examined in more detail to give context to the phrase ‘government by public relations.’     

DNA COLLECTION IN A RANDOMIZED SOCIAL SCIENCE STUDY OF COLLEGE PEER EFFECTS

We describe the DNA collection processes of an initial pilot and full study, which is designed to investigate joint peer and genetic effects on health behaviors and attitudes in a college campus setting. In the main study, 2664 (79.5%) students completed a Web survey and 2080 (78.7% of the survey completers after adjusting for the ineligible) provided a saliva DNA sample. The response rate for completing both the survey and the DNA portion of the study is 62.5%. Our DNA yields are of high quality. Overall, our experiences and results demonstrate that genetic data can be successfully collected as a part of traditional social science survey research projects. To aid others in doing so, we provide extensive details of our data collection experiences and offer recommendations to future researchers seeking to do or evaluate similar work.