Allowing for non-ignorable non-response in the analysis of voting intention data

We apply some log-linear modelling methods, which have been proposed for treating non-ignorable non-response, to some data on voting intention from the British General Election Survey. We find that, although some non-ignorable non-response models fit the data very well, they may generate implausible point estimates and predictions. Some explanation is provided for the extreme behaviour of the maximum likelihood estimates for the most parsimonious model. We conclude that point estimates for such models must be treated with great caution. To allow for the uncertainty about the non-response mechanism we explore the use of profile likelihood inference and find the likelihood surfaces to be very flat and the interval estimates to be very wide. To reduce the width of these intervals we propose constraining confidence regions to values where the parameters governing the non-response mechanism are plausible and study the effect of such constraints on inference. We find that the widths of these intervals are reduced but remain wide.     

Swept Out: Measuring Rurality and Migration Intentions on the Upper Great Plains

Rural America has long been conceptualized as a place of out‐migration, a process that is the subject of many popular sociological works and remains a dominating narrative that describes rural life in the United States today. Population trends demonstrate this migration pattern for nearly the past century; however, emerging data paint a complex picture of migration behavior and intentions in rural areas. In this article, we utilize several measures of rurality to analyze the results of a 2012 mail survey (n = 2487) that describe the migration intentions of both rural and urban South Dakotans. Our findings show that urban residents are more likely to have intentions to migrate than rural residents, and that drivers of migration intentions appear similar in both urban and rural contexts. The survey also sheds light on the influence of community attachment, community satisfaction, quality of life, and other community strengths and weaknesses that rural and urban residents perceive in their communities. Supporting recent research on rural migration intentions, these results do not suggest high rates of out‐migration in rural areas. We discuss rural America's recent identity as a place of out‐migration, share our survey results, and discuss implications for future rural migration research.     

The smooth colonel and the reverend find common ground

A semiparametric regression estimator that exploits categorical (i.e., discrete-support) kernel functions is developed for a broad class of hierarchical models including the pooled regression estimator, the fixed-effects estimator familiar from panel data, and the varying coefficient estimator, among others. Separate shrinking is allowed for each coefficient. Regressors may be continuous or discrete. The estimator is motivated as an intuitive and appealing generalization of existing methods. It is then supported by demonstrating that it can be realized as a posterior mean in the Lindley and Smith (1972 Lindley, D. V., Smith, A. F. M. (1972). Bayes estimates for the linear model. Journal of the Royal Statistical Society 34:1–41. [Google Scholar]) framework. As a demonstration of the flexibility of the proposed approach, the model is extended to nonparametric hierarchical regression based on B-splines.     

Gamblers Anonymous as a Recovery Pathway: A Scoping Review

Given the preponderance of Gamblers Anonymous (GA), there has been relatively little effort to explore the existing evidence base on its effectiveness as a recovery approach for problem gambling. To remedy this gap in the literature we conducted a scoping review of the literature on mutual aid for individuals experiencing problem gambling published between 2002 and 2015. We searched 13 databases and reviewed reference lists and websites of relevant organizations. We reviewed records for eligibility and extracted relevant data from eligible articles. Three reviewers independently assessed the methodological quality of the included studies using the Mixed Methods Appraisal Tool. We identified 17 studies in 25 publications that were eligible for inclusion. Most studies were conducted in the United States, were cross-sectional in design, and involved both male and female adult participants. Results indicate that the evidence for the effectiveness of GA either as a control condition or in conjunction with formal treatment or medication is inconsistent. An emphasis on patience, using the Serenity Prayer as a way to gain acceptance of financial matters and reality, and absolute assertion of identity as a “compulsive gambler” were identified as important aspects of GA’s recovery culture. There is a need for large-scale randomized controlled trials to determine GA’s effectiveness, as well as research exploring the mechanisms through which GA works, barriers to GA as a recovery approach, and the status of women in the fellowship.     

Which Diagnostic Criteria are Most Useful in Discriminating Between Social Gamblers and Individuals with Gambling Problems? An Examination of DSM-IV and DSM-5 Criteria

The current study sought to identify which diagnostic criteria for gambling disorder have the greatest ability to differentiate between social and problem gamblers. This study was conducted on a sample of male and female college student athletes across the U.S. (n = 8674). Classification and regression tree analysis represents an appropriate technique when addressing the question of an item’s diagnostic value, as it sequentially selects variables to isolate sets of observations with similar outcomes. The current results suggest that the item related to preoccupation (“Have there been periods in the past year where you spent a lot of time thinking about gambling?”) was the DSM-5 item best able to differentiate between male and female social and problem gamblers in this sample. When considering only the nine criteria retained in the DSM-5, three criteria were identified as key for distinguishing between social and disordered gamblers among men, and one criterion was identified for distinguishing between groups of women. In addition, these results do not support the notion that the illegal acts criterion has a particularly low base rate and found that it can be an important indicator of disordered gambling in a college-aged sample.     

An evidential approach to non-inferiority clinical trials

We present likelihood methods for defining the non-inferiority margin and measuring the strength of evidence in non-inferiority trials using the 'fixed-margin' framework. Likelihood methods are used to (1) evaluate and combine the evidence from historical trials to define the non-inferiority margin, (2) assess and report the smallest non-inferiority margin supported by the data, and (3) assess potential violations of the constancy assumption. Data from six aspirin-controlled trials for acute coronary syndrome and data from an active-controlled trial for acute coronary syndrome, Organisation to Assess Strategies for Ischemic Syndromes (OASIS-2) trial, are used for illustration. The likelihood framework offers important theoretical and practical advantages when measuring the strength of evidence in non-inferiority trials. Besides eliminating the influence of sample spaces and prior probabilities on the 'strength of evidence in the data', the likelihood approach maintains good frequentist properties. Violations of the constancy assumption can be assessed in the likelihood framework when it is appropriate to assume a unifying regression model for trial data and a constant control effect including a control rate parameter and a placebo rate parameter across historical placebo controlled trials and the non-inferiority trial. In situations where the statistical non-inferiority margin is data driven, lower likelihood support interval limits provide plausibly conservative candidate margins.     

Towards optimal scaling of metropolis-coupled Markov chain Monte Carlo

We consider optimal temperature spacings for Metropolis-coupled Markov chain Monte Carlo (MCMCMC) and Simulated Tempering algorithms. We prove that, under certain conditions, it is optimal (in terms of maximising the expected squared jumping distance) to space the temperatures so that the proportion of temperature swaps which are accepted is approximately 0.234. This generalises related work by physicists, and is consistent with previous work about optimal scaling of random-walk Metropolis algorithms.