Asymmetric Forecast Densities for U.S. Macroeconomic Variables from a Gaussian Copula Model of Cross-Sectional and Serial Dependence

Most existing reduced-form macroeconomic multivariate time series models employ elliptical disturbances, so that the forecast densities produced are symmetric. In this article, we use a copula model with asymmetric margins to produce forecast densities with the scope for severe departures from symmetry. Empirical and skew t distributions are employed for the margins, and a high-dimensional Gaussian copula is used to jointly capture cross-sectional and (multivariate) serial dependence. The copula parameter matrix is given by the correlation matrix of a latent stationary and Markov vector autoregression (VAR). We show that the likelihood can be evaluated efficiently using the unique partial correlations, and estimate the copula using Bayesian methods. We examine the forecasting performance of the model for four U.S. macroeconomic variables between 1975:Q1 and 2011:Q2 using quarterly real-time data. We find that the point and density forecasts from the copula model are competitive with those from a Bayesian VAR. During the recent recession the forecast densities exhibit substantial asymmetry, avoiding some of the pitfalls of the symmetric forecast densities from the Bayesian VAR. We show that the asymmetries in the predictive distributions of GDP growth and inflation are similar to those found in the probabilistic forecasts from the Survey of Professional Forecasters. Last, we find that unlike the linear VAR model, our fitted Gaussian copula models exhibit nonlinear dependencies between some macroeconomic variables. This article has online supplementary material.     

Stochastically optimal bootstrap sample size for shrinkage-type statistics

In nonregular problems where the conventional \(n\) out of \(n\) bootstrap is inconsistent, the \(m\) out of \(n\) bootstrap provides a useful remedy to restore consistency. Conventionally, optimal choice of the bootstrap sample size \(m\) is taken to be the minimiser of a frequentist error measure, estimation of which has posed a major difficulty hindering practical application of the \(m\) out of \(n\) bootstrap method. Relatively little attention has been paid to a stronger, stochastic, version of the optimal bootstrap sample size, defined as the minimiser of an error measure calculated directly from the observed sample. Motivated by this stronger notion of optimality, we develop procedures for calculating the stochastically optimal value of \(m\). Our procedures are shown to work under special forms of Edgeworth-type expansions which are typically satisfied by statistics of the shrinkage type. Theoretical and empirical properties of our methods are illustrated with three examples, namely the James–Stein estimator, the ridge regression estimator and the post-model-selection regression estimator.     

Methods to assess measurement error in questionnaires of sedentary behavior

Sedentary behavior has already been associated with mortality, cardiovascular disease, and cancer. Questionnaires are an affordable tool for measuring sedentary behavior in large epidemiological studies. Here, we introduce and evaluate two statistical methods for quantifying measurement error in questionnaires. Accurate estimates are needed for assessing questionnaire quality. The two methods would be applied to validation studies that measure a sedentary behavior by both questionnaire and accelerometer on multiple days. The first method fits a reduced model by assuming the accelerometer is without error, while the second method fits a more complete model that allows both measures to have error. Because accelerometers tend to be highly accurate, we show that ignoring the accelerometer's measurement error, can result in more accurate estimates of measurement error in some scenarios. In this article, we derive asymptotic approximations for the mean-squared error of the estimated parameters from both methods, evaluate their dependence on study design and behavior characteristics, and offer an R package so investigators can make an informed choice between the two methods. We demonstrate the difference between the two methods in a recent validation study comparing previous day recalls to an accelerometer-based ActivPal.     

“It has given me life.” Latinas and the U-Visa: A Qualitative Study

Women, particularly undocumented women, are at an increased risk for gender-based violence including intimate partner violence (IPV). Women’s lack of legal immigration status is often used as a tool of dominance and control of undocumented women. The Victim of Trafficking and Violence Prevention Act 2000 created the U-Visa that provides undocumented IPV victims with lawful immigration status if they are willing to assist authorities in investigating crimes. The objective of this study is to better understand the benefits of obtaining the U-Visa from the perspectives of Latina U-Visa recipients who are survivors of IPV. In this community-based qualitative research study involving IPV survivors, community leaders, service providers and academics, we collected qualitative data through interviews with 20 participants including 15 survivors of IPV who were U-Visa recipients. Interviews were digitally-recorded, transcribed and translated, and analyzed using a qualitative software to develop key themes. Women received a $20 gift card as a token of appreciation for their participation in this study. Findings highlight key benefits such as improved mental health, renewed confidence and self-esteem, self-confidence, less perceived exploitation, access to better jobs and housing, freedom to travel, and improved economic and social well-being for visa recipients and their families. Obtaining the U-Visa was a transformative and life-changing experience for Latina survivors of IPV. Social policies such as TVPA help support vulnerable women who are victims of IPV.     

Association of sexual abstinence in adolescence with mental health in adulthood

We examined whether adolescent sexual abstinence predicts better adult mental health. 1,917 adolescents, recruited from middle schools at age 13, were surveyed at ages 13, 18, 23, and 29. In bivariate analyses, adolescent sexual abstinence was associated with better mental health at age 29 for females, but not males; three adolescent factors, educational prospects, family bonding, and unconventionality were investigated as explanatory variables of this relationship. The abstinence-mental health relationship was nonsignificant when educational prospects was included in multivariate models, and marginally significant when family bonding and unconventionality were included; all three explanatory factors accounted for significant proportions of the variance in adult mental health. Girls who are uninvolved in school, have weak family backgrounds, and exhibit unconventionality may have poor adult mental health, whether or not they abstain from sex in adolescence. Interventions that strengthen adolescents' connections to families and schools may reduce risk for long-term mental health problems.     

Domestic violence screening and service acceptance among adult victims in a dependency court setting

Many child welfare systems are unable to effectively identify and address co-occurring domestic violence and child maltreatment. In response, the Dependency Court Intervention Program for Family Violence implemented a protocol to identify indicators of domestic violence in families involved with child protection proceedings. This article highlights data that demonstrate the ability of an outreach and screening process to identify adult victims of domestic violence in dependency court and to offer them appropriate intervention services.     

Applying the use of activity in the assessment of malingering: A case illustration

The assessment of malingering has predominantly been considered within the domains of neuropsychologists and psychiatrists, who use consistency of performance criteria similar to those used in functional capacity evaluations (FCE). The use of activity has traditionally been used in occupational therapy as an assessment and treatment modality with goals not always considered obvious and which could easily be used for diversional reasons. The appropriate use of activity adds an additional dimension to a layered approach of using multiple data sources and methods as recommended by FCE practitioners and neuropsychologists alike. The case illustration aims to explain the above using a layered model.     

Dopamine Genes and Pathological Gambling in Discordant Sib-Pairs

Pathological gambling (PG) is an impulse control disorder that has been considered as a behavioral addiction. Recent studies have suggested the involvement of the dopaminergic system in addictions and impulse control disorders and associations of dopamine receptor genes (DRD1, DRD2, and DRD4) and PG have been reported. In the present study, 140 sib-pairs discordant for the diagnosis of PG (70 males and 70 females on each group) were recruited through the Gambling Outpatient Unit at the Institute of Psychiatry, University of Sao Paulo and were assessed by trained psychiatrists. A family-based association design was chosen to prevent population stratification. All subjects were genotyped for dopamine receptor genes (DRD1 -800 T/C, DRD2 TaqIA RFLP, DRD3 Ser9Gly, DRD4 48bp exon III VNTR, DRD5 (CA) repeat) and the dopamine transporter gene (SCL6A3 40 bp VNTR). Our results suggest the association of PG with DRD1 -800 T/C allele T (P = .03).     

Effects of at-work exercises on computer operators

At-work exercises are commonly recommended for computer operators. This randomized control trial assessed adherence, pain and satisfaction after 4 weeks of at-work exercise. Subjects (n=72) were randomized into 3 groups: resistance exercise, stretching, and control. Outcomes included a satisfaction survey, a visual analogue pain scale (VAS), a pain drawing, and the Neck Disability Index (NDI). The VAS, the drawing, and NDI were analyzed together as a composite variate referred to as Pain Impact. Exercise frequency was similar across the 3 groups (median=1.5 times per day). No differences were found between groups on Pain Impact p=0.714) or individual pain variables. Most satisfaction survey item scores did not differ between groups. However, a significant difference between groups on the survey item related to discomfort. The resistance and stretching group differed from the control group with regard to their perception that the exercises were helpful in reducing discomfort in the back and neck (p<0.001). We conclude that most subjects found the resistance and the stretching exercises easy to do, performed them 1 to 2 times daily, and said they reduced discomfort. To determine optimal type and frequency of at-work exercises, further study is needed.