The Impact of Student Loan Debt and Student Loan Delinquency on Total,Sex‐, and Age‐specific Suicide Rates during the Great Recession

In 2012, the outstanding student loan balance in the United States surpassed $1 trillion, and between 2005 and 2012, the student loan delinquency rate increased by 77 percent. Simultaneously, by the end of the 2005–2012 time period, the total suicide rate in the United States reached the highest levels in more than a decade. To investigate the recent trends in student loans and suicide, this paper examined the association between state‐level student loan debt, student loan delinquency, and total, age‐, and sex‐specific suicide rates. The study used a hybrid (decompositional) longitudinal regression approach to examine the relationship between student loan debt, delinquency, and suicide rates during the 2005–2012 time period. The results showed student loan delinquency had a positive and significant effect on several of the suicide rates examined within states but had no effect on suicide rates between states net of controls. The results also showed student loan debt had a significant and negative association with suicide for people ages 20–24 and 25–34.     

The Digital Practices of Mobile Phones

From a global perspective, the mobile phone is by far the most widely used information and communication technology (ICT). People in both developed and developing nations have found ways to integrate the mobile phone into their daily lives. Despite the ubiquity of the mobile phone, the cultural impact of the mobile phone in and of itself has not been a major topic within the sociology of culture. To this end, there are two goals of this paper. First, three common uses of the mobile phone are presented. To separate cultural practices associated with mobile phones from practices associated with other domains of social life, the term digital practices is used. Second, this paper will discuss the domestication of technology approach, and its applicability to the study of mobile phones. Identifying practices and providing a framework for interpreting these practices can help scholars interested in theorizing and teaching the cultural (as opposed to economic or technological) aspects of mobile telephony.     

Missing-Data Adjustments in Large Surveys

Useful properties of a general-purpose imputation method for numerical data are suggested and discussed in the context of several large government surveys. Imputation based on predictive mean matching is proposed as a useful extension of methods in existing practice, and versions of the method are presented for unit nonresponse and item nonresponse with a general pattern of missingness. Extensions of the method to provide multiple imputations are also considered. Pros and cons of weighting adjustments are discussed, and weighting-based analogs to predictive mean matching are outlined.     

Food Calorie Intake under Grain Price Uncertainty in Rural Nepal

This study evaluated the effects of grain output price uncertainty on the farm income of rural households and, consequently, how this uncertainty influenced caloric intake through changes in farm income. Using a national rural household survey data set in Nepal, augmented with output price uncertainty measures calculated from historical time-series data, we found that grain output price uncertainty (especially for rice and wheat) tends to decrease crop production income of rural households. In addition, we found that lower crop income from production decreases calorie intake of rural households. Taken together, these results suggest that output price uncertainty during the production process tends to reduce caloric intake of rural Nepalese households. The price uncertainty seemed to reduce the crop income households need to buy calorie-rich staple foods.     

Estimating Causal Effects in Trials Involving Multi-Treatment Arms Subject to Non-compliance: A Bayesian framework

Data analysis for randomized trials including multi-treatment arms is often complicated by subjects who do not comply with their treatment assignment. We discuss here methods of estimating treatment efficacy for randomized trials involving multi-treatment arms subject to non-compliance. One treatment effect of interest in the presence of non-compliance is the complier average causal effect (CACE) (Angrist et al. 1996), which is defined as the treatment effect for subjects who would comply regardless of the assigned treatment. Following the idea of principal stratification (Frangakis & Rubin 2002), we define principal compliance (Little et al. 2009) in trials with three treatment arms, extend CACE and define causal estimands of interest in this setting. In addition, we discuss structural assumptions needed for estimation of causal effects and the identifiability problem inherent in this setting from both a Bayesian and a classical statistical perspective. We propose a likelihood-based framework that models potential outcomes in this setting and a Bayes procedure for statistical inference. We compare our method with a method of moments approach proposed by Cheng & Small (2006) using a hypothetical data set, and further illustrate our approach with an application to a behavioral intervention study (Janevic et al. 2003).     

Patients' race, ethnicity, language, and trust in a physician

We examine whether racial/ethnic/language-based variation in measured levels of patients' trust in a physician depends on the survey items used to measure that trust. Survey items include: (1) a direct measure of patients' trust that the doctor will put the patient's medical needs above all other considerations, and (2) three indirect measures of trust asking about expectations for specific physician behaviors, including referring to a specialist, being influenced by insurance rules, and performing unnecessary tests. Using a national survey, we find lower scores on indirect measures of trust in a physician among minority users of health care services than among non-Hispanic white users. In contrast, the direct measure of trust does not differ among non-Hispanic whites and nonwhites once we control for potential confounding factors. The results indicate that racial/ethnic/language-based differences exist primarily in those aspects of patients' trust in a physician that reflect specific physician behaviors.     

Design by legislation: The ideological nature of house planning in the United Kingdom, 1918–1961

The official recommendations standards and legislation which have been related to the provision of houses in England have made explicit references to the spatial form and use of domestic facilities. For example, the serial of health and housing legislation during the last two centuries has had an influence upon the designs of houses built during that time, and particularly since the publication of the Tudor Walters Report in 1918. This paper studies the intentions of the series of recommendations and legislation from 1918 until the publication of the Parker Morris Report in 1961. The paper shows how the designs of houses in these official documents express specific ideas upheld by members of the architectural profession and civil servants which can be contrasted with public values about the meaning and use of domestic space.     

Sequential imputation for models with latent variables assuming latent ignorability

Models that involve an outcome variable, covariates, and latent variables are frequently the target for estimation and inference. The presence of missing covariate or outcome data presents a challenge, particularly when missingness depends on the latent variables. This missingness mechanism is called latent ignorable or latent missing at random and is a generalisation of missing at random. Several authors have previously proposed approaches for handling latent ignorable missingness, but these methods rely on prior specification of the joint distribution for the complete data. In practice, specifying the joint distribution can be difficult and/or restrictive. We develop a novel sequential imputation procedure for imputing covariate and outcome data for models with latent variables under latent ignorable missingness. The proposed method does not require a joint model; rather, we use results under a joint model to inform imputation with less restrictive modelling assumptions. We discuss identifiability and convergence‐related issues, and simulation results are presented in several modelling settings. The method is motivated and illustrated by a study of head and neck cancer recurrence. Imputing missing data for models with latent variables under latent‐dependent missingness without specifying a full joint model.