Efficient Markov chain Monte Carlo with incomplete multinomial data

We propose a block Gibbs sampling scheme for incomplete multinomial data. We show that the new approach facilitates maximal blocking, thereby reducing serial dependency and speeding up the convergence of the Gibbs sampler. We compare the efficiency of the new method with the standard, non-block Gibbs sampler via a number of numerical examples.     

Objective Bayesian hypothesis testing in regression models with first-order autoregressive residuals

This article considers the objective Bayesian testing in the normal regression models with first-order autoregressive residuals. We propose some solutions based on a Bayesian model selection procedure to this problem where no subjective input is considered. We construct the proper priors for testing the autocorrelation coefficient based on measures of divergence between competing models, which is called the divergence-based (DB) priors and then propose the objective Bayesian decision-theoretic rule, which is called the Bayesian reference criterion (BRC). Finally, we derive the intrinsic test statistic for testing the autocorrelation coefficient. The behavior of the Bayes factor-based DB priors is examined by comparing with the BRC in a simulation study and an example.     

Does an Immigrant Background Ameliorate Racial Disadvantage? The Socioeconomic Attainments of Second‐Generation African Americans1

Although there is a growing literature on the socioeconomic circumstances of the second generation, this issue has not been systematically considered for African Americans. To help fill this research gap, we investigate the extent to which the socioeconomic attainments of second‐generation African Americans differ from mainstream (i.e., third and higher generation) African Americans. Using data from the Current Population Survey and the 2000 Census, our results indicate that the schooling and wages of second‐generation African Americans consistently exceed those of third‐ and higher generation African Americans. Our findings also reveal that second‐generation African Americans do at least as well as whites in terms of years of schooling, but wage differentials differ significantly by gender. Second‐generation African‐American women earn wages that are at least as high as comparable white women, but second‐generation African‐American men earn wages that are, on average, about 16% less than measurably comparable white men. While no one theoretical perspective can account for all these results, they nonetheless indicate the continuing significance of racial disadvantage for African‐American men, including those with an immigrant background.     

An Effective Statistical Approach for Comparative Risk Assessment1

Comparative risk assessment is an evaluation process designed to rank environmental problems based on the severity of potential hazards. The purpose of this paper is to provide an effective statistical approach to analyze perceived environmental risks. Environmental problems, evaluative criteria, and other potential moderator variables need to be determined first, and then the risk perception data collected. Repeated measures analysis is used to first test for interactions between environmental problems and potential moderator variables. If there are no significant interactions, then the risk difference among environmental problems is tested unconditionally; otherwise the risk difference is tested conditionally. Cluster analysis for environmental problems is performed only when the risk difference is significant. The clustering results can be objectively determined by using the simultaneous T² confidence intervals. Risk-based priority setting is made according to the clusters obtained. To illustrate this approach, an empirical study of comparative socioeconomic risks in Taiwan was conducted. Socioeconomic impacts areas including social security, quality of life, production cost, investment willingness, and economic resources are used as evaluative criteria. Results indicate that selected impact areas do affect relative risk differences among 24 environmental problems, and the difference is significant for each area. Therefore, cluster analysis is conducted separately for each impact area. Risk-based priority settings for clusters of environmental problems are reported.     

Sports PR in message boards on Major League Baseball websites

Message boards are possible places for sports fans to actively express and exchange their opinions. The purpose of this study is to explore the typology of message board uses on sports websites. The analysis of 1350 topics on eight Major League Baseball teams’ websites for 10 days revealed that: (1) the cognitive need of using message boards in a sports organization's website was an outstanding motivation; (2) sharing opinions was a new motivation category (compared to traditional uses and gratifications) that was found to be dominant; and (3) winning teams and losing teams’ message boards were significantly different in terms of number of topics, number of users, and optimism score; however, messages seemed to be optimistic. Implications for public relations practitioners suggest that the message board is an excellent monitoring tool for them as well as a fine communication tool between sports organizations and fans.     

Noninformative priors for linear combinations of the normal means

In this paper, we develop noninformative priors for linear combinations of the means under the normal populations. It turns out that among the reference priors the one-at-a-time reference prior satisfies a second order probability matching criterion. Moreover, the second order probability matching priors match alternative coverage probabilities up to the second order and are also HPD matching priors. Our simulation study indicates that the one-at-a-time reference prior performs better than the other reference priors in terms of matching the target coverage probabilities in a frequentist sense.     

Designing np control charts

This paper presents the results of a simulation approach to the design of economic attribute control charts. The approach taken differs from the classical studies reported in the literature in two respects. First, the often made assumption that the out-of-control state of a process will remain so until detection is relaxed. This in effect allows the average proportion of defectives to deteriorate further before the out-of-control state is detected. Second, there is no requirement for detailed information on the exact process behaviour in the out-of-control state. It is assumed that a multitude of out-of-control causes exist and that the proportion defective is equally likely to be within a specified range of values. The relaxation of these two assumptions makes the model realistic and gives it wide practical applications in the control of a manufacturing process. The simulation computer programs developed are sufficiently compact to run on the low cost microcomputers.     

Differences in Sexual Guilt and Desire in East Asian and Euro-Canadian Men

Differences in sexual desire between individuals of East Asian and European descent are well-documented, with East Asian individuals reporting lower sexual desire. The mechanisms that underlie this disparity have received little empirical attention. Recent research has found that sex guilt, “a generalized expectancy for self-mediated punishment for violating or for anticipating violating standards of proper sexual conduct” (Mosher &; Cross, 1971 Mosher , D. L. , &; Cross , H. J. ( 1971 ). Sex guilt and premarital sexual experiences of college students . Journal of Consulting and Clinical Psychology , 36 , 27 – 32 . doi: 10.1037/h0030454 [Crossref], [PubMed], [Web of Science ®] , [Google Scholar], p. 27), mediates the relationship between culture and sexual desire in East Asian and Euro-Canadian women. The goal of this study was to explore this role of sex guilt in men. Male Euro-Canadian (n = 38) and East Asian (n = 45) university students completed online questionnaires. The East Asian men reported significantly lower sexual desire and significantly higher sex guilt. Sex guilt was a significant mediator of the relationship between ethnicity and sexual desire, as well as a significant mediator between mainstream acculturation and sexual desire. Among the East Asian men, mainstream acculturation was significantly and negatively correlated with sex guilt such that increasing mainstream acculturation was associated with less sex guilt. The diagnostic and clinical implications of the findings are discussed.     

A matching prior for the product of normal means based on the modified profile likelihood

In this paper, we develop a matching prior for the product of means in several normal distributions with unrestricted means and unknown variances. For this problem, properly assigning priors for the product of normal means has been issued because of the presence of nuisance parameters. Matching priors, which are priors matching the posterior probabilities of certain regions with their frequentist coverage probabilities, are commonly used but difficult to derive in this problem. We developed the first order probability matching priors for this problem; however, the developed matching priors are unproper. Thus, we apply an alternative method and derive a matching prior based on a modification of the profile likelihood. Simulation studies show that the derived matching prior performs better than the uniform prior and Jeffreys’ prior in meeting the target coverage probabilities, and meets well the target coverage probabilities even for the small sample sizes. In addition, to evaluate the validity of the proposed matching prior, Bayesian credible interval for the product of normal means using the matching prior is compared to Bayesian credible intervals using the uniform prior and Jeffrey’s prior, and the confidence interval using the method of Yfantis and Flatman.     

On asymptotic properties of Bayesian partially linear models

In this paper, we present large sample properties of a partially linear model from the Bayesian perspective, in which responses are explained by the semiparametric regression model with the additive form of the linear component and the nonparametric component. For this purpose, we investigate asymptotic behaviors of posterior distributions in terms of consistency. Specifically, we deal with a specific Bayesian partially linear regression model with additive noises in which the nonparametric component is modeled using Gaussian process priors. Under the Bayesian partially linear model using Gaussian process priors, we focus on consistency of posterior distribution and consistency of the Bayes factor, and extend these results to generalized additive regression models and study their asymptotic properties. In addition we illustrate the asymptotic properties based on empirical analysis through simulation studies.