Confidence intervals based on the deviance statistic for the hyperparameters in state space models

The main objective of this work is to evaluate the performance of confidence intervals, built using the deviance statistic, for the hyperparameters of state space models. The first procedure is a marginal approximation to confidence regions, based on the likelihood test, and the second one is based on the signed root deviance profile. Those methods are computationally efficient and are not affected by problems such as intervals with limits outside the parameter space, which can be the case when the focus is on the variances of the errors. The procedures are compared to the usual approaches existing in the literature, which includes the method based on the asymptotic distribution of the maximum likelihood estimator, as well as bootstrap confidence intervals. The comparison is performed via a Monte Carlo study, in order to establish empirically the advantages and disadvantages of each method. The results show that the methods based on the deviance statistic possess a better coverage rate than the asymptotic and bootstrap procedures.     

Extending Bayesian back-calculation to estimate age and time specific HIV incidence

Lifetime Data Analysis - CD4-based multi-state back-calculation methods are key for monitoring the HIV epidemic, providing estimates of HIV incidence and diagnosis rates by disentangling their...     

A reflected feature space for CART

We present an algorithm for learning oblique decision trees, called HHCART(G). Our decision tree combines learning concepts from two classification trees, HHCART and Geometric Decision Tree (GDT). HHCART(G) is a simplified HHCART algorithm that uses linear structure in the training examples, captured by a modified GDT angle bisector, to define splitting directions. At each node, we reflect the training examples with respect to the modified angle bisector to align this linear structure with the coordinate axes. Searching axis parallel splits in this reflected feature space provides an efficient and effective way of finding oblique splits in the original feature space. Our method is much simpler than HHCART because it only considers one reflected feature space for node splitting. HHCART considers multiple reflected feature spaces for node splitting making it more computationally intensive to build. Experimental results show that HHCART(G) is an effective classifier, producing compact trees with similar or better results than several other decision trees, including GDT and HHCART trees.     

Twenty Years of Economics Curriculum: Trends,Issues, and Transformations?

This is a comprehensive review of literature related to K-12 economics curriculum spanning 20 years, from 1998-2018. The search for literature revealed 18 articles and book chapters in peer-reviewed journals and volumes related to social studies and economics education. The study revealed several trends and issues related to K-12 economics textbooks, including publishing trends, the extent to which economics curriculum is relevant and enactive, and the influence of neoclassical economic theory in serving as the “official knowledge” undergirding the curriculum. The review presents debates in the field related to these issues. The study also reveals the possible influence of the 2008 financial crisis, revealing that economics curriculum seems to have changed little, although the number of scholars critiquing the curriculum has risen dramatically.     

SODA WARS: THE EFFECT OF A SODA TAX ELECTION ON UNIVERSITY BEVERAGE SALES

We examine how soda sales changed due to the campaign attention and election outcome of a local excise tax on sugar‐sweetened beverages. Using panel data of beverage sales from university retailers in Berkeley, California, we estimate that soda purchases relative to control beverages significantly dropped immediately after the election, months before the tax was implemented in the city of Berkeley or on campus. Supplemental scanner data from off‐campus retailers reveal this result is not unique to the university setting. Our findings suggest soda tax media coverage and election outcomes can have larger effects on purchasing behavior than the tax itself. (JEL D12, H20, C23, I38, Q18)     

Trajectories of Interracial Heterosexual Couples: A Longitudinal Analysis of Relationship Quality and Separation

Minimal research has examined interracial couples’ relationship satisfaction and dissolution patterns over time. Using dyadic data across 8 years, we examined potential differences in relationship quality trajectories through latent growth curve modeling with 1,336 couples as well as differential risks for relationship dissolution through logistic regression between same‐race and interracial relationships using a different subset of 2,370 couples. Results indicated that women in interracial relationships were significantly lower in initial relationship quality than women in same‐race relationships. Further, interracial couples of Black‐Hispanic partnerings were twice as likely to separate across 8 years than same‐race couples. These results suggest that despite interracial relationships not substantively differing from same‐race couples in trajectories of relationship quality, specific Black‐Hispanic interracial couples are at a higher risk of eventual separation.     

Association between sexually explicit messages and sleep health among French sexual minority men

It has been demonstrated that sexual minority men (SMM) participate in sexting. While research has shown that engagement in the exchange of sexually explicit media is associated with poor health outcomes, no previous research has investigated its association with sleep health outcomes. This study sought to examine the association between sexually explicit media and sleep health among SMM, a population that suffers from poor sleep health. A popular geosocial networking application was used to recruit SMM individuals (N?=?580) in the Paris, France, metropolitan area. Multivariate analyses, adjusting for sociodemographics, were used to test the association between the frequency of sexually explicit messaging and three dimensions of sleep health: (1) sleep quality, (2) sleep duration, and (3) two aspects of sleep problems. In multivariate analyses, those who reported engaging in sexually explicit messaging more were more likely to report getting less than seven?hours of sleep (aRR = 1.24; 95% CI = 1.08, 1.43) compared with those who reported engaging in sexually explicit messaging less. No significant associations were found between sexting and sleep quality or reporting sleep problems. Sexually explicit messaging was associated with shorter sleep duration. Intervention targeted at individuals who sext could potentially improve sleep health outcomes.     

Interplay Between Sensation Seeking and Parental Rules in the Emergence of Heavy Episodic Drinking

This study examined the parallel mediational processes between sensation seeking and parental rules on alcohol, in the emergence of heavy episodic drinking (HED) in adolescents. Data were drawn from a U.K. clustered randomized control trial (control arm only, N ≈ 6,300, M_age at baseline = 12.5). Using parallel process latent growth curve analysis, stricter parental rules at baseline were found to be associated with greater declines in sensation seeking over time and a lower risk of HED at follow‐up (+33 months). Higher initial levels of sensation seeking predicted a faster relaxation of parental rules and a greater risk of HED. By maintaining strict rules about alcohol, parents may promote a positive reduction in sensation seeking and a lower risk of HED.     

Is Sexual Abuse a Unique Predictor of Sexual Risk Behaviors,Pregnancy, and Motherhood in Adolescence?

This study tested sexual abuse as a unique predictor of subsequent adolescent sexual behaviors, pregnancy, and motherhood when in company with other types of maltreatment (physical abuse, neglect) and alternative behavioral, family, and contextual risk factors in a prospective, longitudinal study of maltreated (n = 275) and comparison (n = 239) nulliparous females aged 14–19 years old assessed annually through 19 years old. Hierarchical regression was used to disentangle risk factors that account for the associations of maltreatment type on risky sexual behaviors at 19 years old, adolescent pregnancy, and adolescent motherhood. Findings indicate that sexual and physical abuse remain significant predictors of risky sexual behaviors, and that sexual abuse remains a significant predictor of adolescent motherhood when alternative explanatory variables are controlled.