Semiparametric Estimation in Copulas with the Same Marginals

We consider semiparametric multivariate data models based on copula representation of the common distribution function. A copula is characterized by a parameter of association and marginal distribution functions. This parameter and the marginal distributions are unknown. In this article, we study the estimator of the parameter of association in copulas with the marginal distribution functions assumed as nuisance parameters restricted by the assumption that the components are identically distributed. Results of this work could be used to construct special kinds of tests of homogeneity for random vectors having dependent components.     

Race differentials in employment effects of psychological distress: A study of non-Hispanic Whites and African-Americans in the United States

This study used two sub-samples of African-Americans and non-Hispanic Whites from the 2002–2003 U.S. National Survey on Drug Use and Health to examine differential effects of psychological distress (PD) on employment. Failing to reject exogeneity of PD in the employment specifications, we estimated standard probit of employment. We found that PD significantly reduced employment probability regardless of race; but the reduction was 7.4% for African-Americans, compared to 5.3% for Whites. Using individuals with PD only, we estimated the Oaxaca–Blinder decomposition and found endowments explained 61% of employment differences between Whites with PDs and African-Americans with PDs while 39% of these differences were due to unexplained factors. These findings suggest that targeted policies for prevention and effective treatment of PD might yield higher employment benefits for minorities.     

In college and in recovery: Reasons for joining a Collegiate Recovery Program

ABSTRACT

Objective: Collegiate Recovery Programs (CRPs), a campus-based peer support model for students recovering from substance abuse problems, grew exponentially in the past decade, yet remain unexplored. Methods: This mixed-methods study examines students' reasons for CRP enrollment to guide academic institutions and referral sources. Students (N = 486) from the 29 CRPs nationwide operating in 2012 completed an online survey in 2013. Results: Students were somewhat older than traditional age (mean age = 26). Now sober for 3 years (mean), they had experienced severe dependence on multiple substances. One third reported they would not be in college were it not for a CRP, and 20% would not be at their current institution. Top reasons for joining a CRP were the need for same-age peer recovery support and wanting to “do college sober,” recognizing that college life challenges sobriety. Conclusions: CRPs appear to meet their mission of allowing recovering students to pursue educational goals in “an abstinence hostile environment.” Findings emphasize the need for more institutions to address the support needs of students in recovery.     

Future directions for research into the psychological determinants of problem gambling patterns

Abstract

Rapid increases in the availability of gambling have led to an increased recognition of problem gambling as a major public health concern. A growing body of empirical research has contributed greatly to current knowledge; however, most has centered on prevalence and on risk factors for problem gambling. In this paper, the authors argue for the need to extend the investigative scope of the gambling studies field to improve understanding the natural course of problem gambling over time and to the identification of psychosocial determinants of gambling patterns. Elucidating these issues would constitute an important first step in refining preventive and therapeutic efforts toward curbing possible increases in problem gambling and attendant consequences. Important research areas and methodologies identified in this paper are: large‐scale prospective studies using repeated measures, investigations into factors that may protect from or facilitate progression to problem gambling, especially factors that may be amenable to change, and broadening research samples to community‐based regular gamblers, particularly subclinical (in transition) individuals.     

Through the Lens of Sexual Stigma: Attitudes Toward Lesbian and Gay Parenting

Drawing from the literature on sexual stigma, the principal aim of this study was to investigate predictors of heterosexual's internalization of negative attitudes regarding lesbian and gay parenting and the mediating role of beliefs in the controllability of homosexuality. A Portuguese sample of 1,430 heterosexual women and 502 heterosexual men responded to an online questionnaire about attitudes toward lesbian and gay parenting. Structural equation modeling was used to explore attitudinal predictors and mediation analysis. Mediation analyses revealed that sexual prejudice toward same-gender-parented families was predicted by gender, age, education, and religiosity, in that heterosexual men, those who were older, had less education, and were more religious held significantly more negative beliefs about lesbian and gay parenting, as well as lower perception of benefits associated with lesbian and gay parenting. Further, etiological beliefs mediated the effects of gender, age, and religiosity on sexual attitudes, highlighting the importance of the perception of controllability of homosexuality in justifying sexual prejudice.     

Metabolic and hormonal responses to different resistance training systems in elderly men

Objective: To compare acute and sub-acute responses in hormonal profile and metabolic parameters in elderly people who participated in two methods of strength training (ST) with equalized loads.

Methods and materials: A total of 12 elder individuals (65?±?3 years) were randomly assigned to two training methods: constant intensity (CI, 3 sets of 10 repetitions with 75% of 1RM) and variable intensity (VI, 1st set: 12 repetitions at 67% of 1RM?>?2nd set: 10 repetitions at 75% of 1RM and 3rd set: 8 repetitions at 80% of 1RM). Both methods included the following exercises: leg press, knee extension, and squat with 1?min rest intervals between sets. Free speed of execution and maximum range of movement were encouraged throughout each set for both protocols. Blood samples were analyzed included glucose, testosterone (T), cortisol (C), T/C rate, growth hormone (GH), and lactate at 2 and 24?h post intervention.

Results: There were no observed differences in glucose, testosterone, GH, and lactate concentrations both at 2 and 24?h after the execution of the two training methods. However, significant increases in the levels of T/C rate and decrease on cortisol were observed immediately post exercise for both protocols.

Conclusions: Although no significant differences were observed between the two interventions in relation to the hormonal and metabolic parameters analyzed, both training methods promoted a favorable response, with a slight superiority noted for the CI method relative to the hormonal profile.     

Bernstein conditional density estimation with application to conditional distribution and regression functions

In this paper we propose a smooth nonparametric estimation for the conditional probability density function based on a Bernstein polynomial representation. Our estimator can be written as a finite mixture of beta densities with data-driven weights. Using the Bernstein estimator of the conditional density function, we derive new estimators for the distribution function and conditional mean. We establish the asymptotic properties of the proposed estimators, by proving their asymptotic normality and by providing their asymptotic bias and variance. Simulation results suggest that the proposed estimators can outperform the Nadaraya–Watson estimator and, in some specific setups, the local linear kernel estimators. Finally, we use our estimators for modeling the income in Italy, conditional on year from 1951 to 1998, and have another look at the well known Old Faithful Geyser data.