Homeless families on the border: A demographic profile

The southwestern borderland region of the United States is characterized by a large immigrant population, high levels of poverty, high unemployment rates, and a growing number of homeless families. In order to assist these families it is necessary to gain information about the demographics and service needs of this population. The aim of this study is to determine the characteristics of homeless families in El Paso using the “point in time” technique. Face to face interviews were conducted with 95 homeless families. The data was compared to information on homeless families presented in Ten Cities, 1997-1998: A Snapshot of Family Homelessness Across America as well as to demographic characteristics of domiciled families in El Paso. What emerges is the unique profile of the homeless family in this southwestern city.     

Bayesian hierarchical model for protein identifications

In proteomics, identification of proteins from complex mixtures of proteins extracted from biological samples is an important problem. Among the experimental technologies, mass spectrometry (MS) is the most popular one. Protein identification from MS data typically relies on a ‘two-step’ procedure of identifying the peptide first followed by the separate protein identification procedure next. In this setup, the interdependence of peptides and proteins is neglected resulting in relatively inaccurate protein identification. In this article, we propose a Markov chain Monte Carlo based Bayesian hierarchical model, a first of its kind in protein identification, which integrates the two steps and performs joint analysis of proteins and peptides using posterior probabilities. We remove the assumption of independence of proteins by using clustering group priors to the proteins based on the assumption that proteins sharing the same biological pathway are likely to be present or absent together and are correlated. The complete conditionals of the proposed joint model being tractable, we propose and implement a Gibbs sampling scheme for full posterior inference that provides the estimation and statistical uncertainties of all relevant parameters. The model has better operational characteristics compared to two existing ‘one-step’ procedures on a range of simulation settings as well as on two well-studied datasets.     

Randomized controlled trial of emotionally focused couple therapy compared to treatment as usual for depression: Outcomes and mechanisms of change

This randomized controlled trial examined the effectiveness of Emotionally Focused Therapy (EFT) for depression and relationship satisfaction versus usual care (i.e., couple therapy other than EFT), and explored mechanisms of change. Mixed model trajectory analyses of 16 couples indicated EFT was associated with greater improvement in relationship satisfaction among men and women. Men receiving EFT reported greater improvements in depressive symptoms compared to usual care. Unified structural equation modeling revealed changes in relationship satisfaction preceded changes in depressive symptoms in one cluster of partners, while changes in depression preceded changes in relationship satisfaction in a second cluster. Two other clusters reported simultaneous changes in satisfaction and depression. This study provides encouraging results on the effectiveness of EFT for depression, and insight into mechanisms of change.     

Random projections for Bayesian regression

This article deals with random projections applied as a data reduction technique for Bayesian regression analysis. We show sufficient conditions under which the entire d-dimensional distribution is approximately preserved under random projections by reducing the number of data points from n to \(k\in O({\text {poly}}(d/\varepsilon ))\) in the case \(n\gg d\). Under mild assumptions, we prove that evaluating a Gaussian likelihood function based on the projected data instead of the original data yields a \((1+O(\varepsilon ))\)-approximation in terms of the \(\ell _2\) Wasserstein distance. Our main result shows that the posterior distribution of Bayesian linear regression is approximated up to a small error depending on only an \(\varepsilon \)-fraction of its defining parameters. This holds when using arbitrary Gaussian priors or the degenerate case of uniform distributions over \(\mathbb {R}^d\) for \(\beta \). Our empirical evaluations involve different simulated settings of Bayesian linear regression. Our experiments underline that the proposed method is able to recover the regression model up to small error while considerably reducing the total running time.     

Be Careful Where You Smile: Culture Shapes Judgments of Intelligence and Honesty of Smiling Individuals

Smiling individuals are usually perceived more favorably than non-smiling ones—they are judged as happier, more attractive, competent, and friendly. These seemingly clear and obvious consequences of smiling are assumed to be culturally universal, however most of the psychological research is carried out in WEIRD societies (Western, Educated, Industrialized, Rich, and Democratic) and the influence of culture on social perception of nonverbal behavior is still understudied. Here we show that a smiling individual may be judged as less intelligent than the same non-smiling individual in cultures low on the GLOBE’s uncertainty avoidance dimension. Furthermore, we show that corruption at the societal level may undermine the prosocial perception of smiling—in societies with high corruption indicators, trust toward smiling individuals is reduced. This research fosters understanding of the cultural framework surrounding nonverbal communication processes and reveals that in some cultures smiling may lead to negative attributions.     

Mapping the two levels of digital divide: Internet access and social network site adoption among older adults in the USA

Older adults have increasingly adopted Internet and social network sites (SNSs), but little communication scholarship has explored systematic differences in access within this population. Using a nationally representative sample of Americans over the age of 50 years from the 2012 Health and Retirement Study, we examine Internet access (N?=?18,851) and SNS adoption patterns (N?=?869) among this sample and explore how these patterns vary by age. Regarding Internet access, results suggest that while the gender divide has reversed in favor of women, older adults who are economically, socioculturally, or physically disadvantaged are less likely to have reliable Internet access. In addition, the view that the various divides in Internet access are less of a concern for those who are younger is only partially supported, as some access-related divides do not vary by age or even decrease with age. For SNS adoption, we found that access to technological resources (diversity of online activities) positively predicts SNS use. Moreover, SNS users are more likely to be younger, female, widowed, and homemakers, perhaps because these individuals are more motivated to use SNSs to complement or compensate for their existing social status. These findings reveal unique challenges and motivations in relation to Internet access and SNS adoption patterns across the later life span.     

Gender Differences in Marital Satisfaction: A Meta‐analysis

The purpose of the present meta‐analysis was to empirically test the widely held assumption that women experience lower marital satisfaction than men. A total of 226 independent samples with a combined sum of 101,110 participants were included in the meta‐analysis. Overall results indicated statistically significant yet very small gender differences in marital satisfaction between wives and husbands, with wives slightly less satisfied than husbands; moderator analyses, however, indicated that this difference was due to the inclusion of clinical samples, with wives in marital therapy 51% less likely to be satisfied with their marital relationship than their husbands. The effect size for nonclinical community‐based samples indicated no significant gender differences among couples in the general population. Additional moderator analyses indicated that there were also no gender differences when the levels of marital satisfaction of husbands and wives in the same relationship (i.e., dyadic data) were compared.     

Naloxone administration for suspected opioid overdose: An expanded scope of practice by a basic life support collegiate-based emergency medical services agency

Opioid abuse is a growing and significant public health concern in the United States. Naloxone is an opioid antagonist that can rapidly reverse the respiratory depression associated with opioid toxicity. Georgetown University's collegiate-based emergency medical services (EMS) agency recently adopted a protocol, allowing providers to administer intranasal naloxone for patients with suspected opioid overdose. While normally not within the scope of practice of basic life support prehospital agencies, the recognition of an increasing epidemic of opioid abuse has led many states, including the District of Columbia, to expand access to naloxone for prehospital providers of all levels of training. In particular, intranasal naloxone is a method of administering this medication that potentially avoids needlestick injuries among EMS providers. Universities with collegiate-based EMS agencies are well positioned to provide life-saving treatments for patients acutely ill from opioid overdose.     

Sufficiency Revisited: Rethinking Statistical Algorithms in the Big Data Era

The big data era demands new statistical analysis paradigms, since traditional methods often break down when datasets are too large to fit on a single desktop computer. Divide and Recombine (D&R) is becoming a popular approach for big data analysis, where results are combined over subanalyses performed in separate data subsets. In this article, we consider situations where unit record data cannot be made available by data custodians due to privacy concerns, and explore the concept of statistical sufficiency and summary statistics for model fitting. The resulting approach represents a type of D&R strategy, which we refer to as summary statistics D&R; as opposed to the standard approach, which we refer to as horizontal D&R. We demonstrate the concept via an extended Gamma–Poisson model, where summary statistics are extracted from different databases and incorporated directly into the fitting algorithm without having to combine unit record data. By exploiting the natural hierarchy of data, our approach has major benefits in terms of privacy protection. Incorporating the proposed modelling framework into data extraction tools such as TableBuilder by the Australian Bureau of Statistics allows for potential analysis at a finer geographical level, which we illustrate with a multilevel analysis of the Australian unemployment data. Supplementary materials for this article are available online.