Using Bayesian graphical models to model biases in observational studies and to combine multiple sources of data: application to low birth weight and water disinfection by-products

Summary.  Data in the social, behavioural and health sciences frequently come from observational studies instead of controlled experiments. In addition to random errors, observational data typically contain additional sources of uncertainty such as missing values, unmeasured confounders and selection biases. Also, the research question is often different from that which a particular source of data was designed to answer, and so not all relevant variables are measured. As a result, multiple sources of data are often necessary to identify the biases and to inform about different aspects of the research question. Bayesian graphical models provide a coherent way to connect a series of local submodels, based on different data sets, into a global unified analysis. We present a unified modelling framework that will account for multiple biases simultaneously and give more accurate parameter estimates than standard approaches. We illustrate our approach by analysing data from a study of water disinfection by-products and adverse birth outcomes in the UK.     

农民工参与城镇医疗保障的行为研究

文章利用农民工调查数据,研究了农民工参与城镇医疗保障的影响因素以及城镇医疗保障对农民工医疗支出决策和医疗费用的影响,考察城镇医疗保障制度是否解决了农民工的医疗保障问题。研究结果发现,自评健康状况很好和很不好的农民工都不愿意参与城镇医疗保障,城镇医疗保障既存在逆向选择,也没有有效分散农民工的医疗风险。农民工是否有医疗支出和医疗费用的多少主要取决于疾病严重程度,农民工参与城镇医疗保障对此没有显著性影响。因此,现行农民工城镇医疗保障制度还没有起到为农民工提供足够的医疗保障作用。     

农民工就业培训调查分析

参加就业培训是农民工顺利实现非农就业的关键,调查显示:农民工受教育程度低,主要以初中、高中文化程度为主;政府部门、用人单位和农民工对就业培训的投资力度较弱,大多数农民工只能从事简单体力劳动;现有劳动力就业培训市场不规范,农民工对其表现出极大不信任;就业培训缺乏灵活性和针对性。构建以农民工、用人单位和政府部门为主体,培训机构、培训市场和就业市场相协调的就业促进型培训模式。利用这一模式,提高农民工综合素质,加大就业培训的投资力度,规范劳动力培训市场建设。     

出生率变化对高等教育的影响研究

建国以来,我国出生率发生了重大转变,随着90年代以来人口出生率的逐年下降,我国高等教育将面临学生数量下滑趋势,未来高等院校将会出现生源不足的困境。但是,由于目前我国高等教育入学率还比较低,加之政府财政时高等教育支持的力度也还有很大提升空阅,因此,尽管出生率会不断下降,但对高等院校整体上生存不会受太大的影响。     

Unacceptable forms of work: A multidimensional model

Unacceptable forms of work (UFW) have been identified as an “area of critical importance” for the ILO as it approaches its centenary. Yet there is currently no comprehensive elaboration of the dimensions, causes or manifestations of UFW. This article reports on a research project that has proposed such a framework. The article first investigates and reconceptualizes key discourses on contemporary work to identify their contribution to an analytically rigorous conception of UFW. It then outlines a novel Multidimensional Model that has been designed for use by local policy actors in identifying and targeting UFW in countries across a range of income levels.     

Who is Jobless? A Comparison of Joblessness in Rural and Urban Areas in China

Since market‐oriented economic reform was launched in China in the 1980s, unemployment has been recognized by the government. This paper focuses on the differences in joblessness in rural and urban areas between rural migrant workers, peasants, and urban citizens. The results indicate that people in rural areas frequently lose their jobs, which differs from the traditional perception. There is a significantly lower jobless rate in urban areas. In contrast to the results of previous studies, the employment situation of rural migrant workers is closer to urban citizens rather than peasants. Logistic regression results show that the elderly, women, and less educated citizens have a higher likelihood of joblessness, both in urban and rural areas. Minorities have a lower likelihood of joblessness in rural areas and a higher likelihood in urban areas. Chinese Communist Party members and people without dependent children have a lower likelihood of joblessness in urban areas.     

Comparison of dichotomized and distributional approaches in rare event clinical trial design: a fixed Bayesian design

This research was motivated by our goal to design an efficient clinical trial to compare two doses of docosahexaenoic acid supplementation for reducing the rate of earliest preterm births (ePTB) and/or preterm births (PTB). Dichotomizing continuous gestational age (GA) data using a classic binomial distribution will result in a loss of information and reduced power. A distributional approach is an improved strategy to retain statistical power from the continuous distribution. However, appropriate distributions that fit the data properly, particularly in the tails, must be chosen, especially when the data are skewed. A recent study proposed a skew-normal method. We propose a three-component normal mixture model and introduce separate treatment effects at different components of GA. We evaluate operating characteristics of mixture model, beta-binomial model, and skew-normal model through simulation. We also apply these three methods to data from two completed clinical trials from the USA and Australia. Finite mixture models are shown to have favorable properties in PTB analysis but minimal benefit for ePTB analysis. Normal models on log-transformed data have the largest bias. Therefore we recommend finite mixture model for PTB study. Either finite mixture model or beta-binomial model is acceptable for ePTB study.     

Women’s attitudes towards the medicalization of childbirth and their associations with planned and actual modes of birth

Problem

Rates of medical interventions in childbirth have greatly increased in the Western world.

The Diffusion of Tolerance: Birth Cohort Changes in the Effects of Education and Income on Political Tolerance

Political tolerance—the willingness to extend civil liberties to traditionally stigmatized groups—is pivotal to the functioning of democracy and the well‐being of members of stigmatized groups. Although political tolerance has traditionally been more common among American elites, we argue that as tolerance has increased, it has also diffused to less educated and less affluent segments of the population. The relative stability of political attitudes over the life course and the socialization of more recent birth cohorts in contexts of increased tolerance suggest that this diffusion of tolerance occurs across birth cohorts rather than time periods. Using age‐period‐cohort models and more than three and a half decades of repeated cross‐sectional survey data, we find persistent and robust across‐cohort declines in the importance of both income and higher education in determining levels of political tolerance. Declines in the effects of socioeconomic status are evident with tolerance toward all five out‐groups in the analysis—anti‐religionists, gays and lesbians, communists, militarists, and racists—but to varying degrees. These findings fit with a model of changes in public opinion, particularly views of civil and political rights, through processes of cultural diffusion and cohort replacement.