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.     

The City of Saskatoon’s Local Area Planning Program: A Case Study

The City of Saskatoon’s Local Area Planning (LAP) Program is a community-based approach to developing comprehensive neighbourhood plans. In order to achieve sustainable and implementable Local Area Plans (LAPs), the City of Saskatoon has been using innovative methods of collaborative decision-making to engage citizens. The program has been recognized nationally by the Federation of Canadian Municipalities for demonstrating innovative approaches to citizen engagement in Sustainable Community Planning. A total of eight LAPs have been adopted by City Council and 212 recommendations have been approved, with 101 of these recommendations being completed, 71 currently in progress and 40 to be determined. Great strides have been made to implement the LAPs by allocating resources for coordinating implementation, working with communities, and for implementing the various recommendations. In addition, over 1,000 people representing various interests have participated in one or more LAP Committee or implementation meetings. Through this participation, partnerships have been formed, program and service delivery has been improved, and most importantly, communities have taken ownership of their plans. After completing eight LAPs, the LAP communities, City Council and city planners have felt the need to measure ongoing changes and progress in the LAP communities. In recognition of this, the City of Saskatoon’s City Planning Branch will be working with LAP communities, the Community-University Institute for Social Research (CUISR) and other stakeholders to develop a framework for statistically measuring changes in LAP communities and to monitor “Neighbourhood Success Factors”. The Neighbourhood Success Factors will work to detect serious socio-economic conditions before they reach a point of crisis. This paper will first describe the LAP Program before reviewing the proposed framework for statistically measuring changes in Saskatoon’s neighbourhoods.

Ethnic segregation in context: Social discrimination among native Dutch pupils and their ethnic minority classmates

Social discrimination, defined as the relative preference for intra-ethnic over inter-ethnic relationships, was studied in pupils’ networks in Dutch secondary school classes. While native Dutch pupils (ethnic majority members) mainly named fellow majority members, ethnic minority members reported ties with as many majority as minority members. Considering the ethnic composition of the classroom, however, majority members discriminated less than minorities. No strong effect of classroom ethnic composition on social discrimination was found, whereas neighborhood composition was shown to clearly influence social discrimination: ethnic minority members were more, and majority members less inclined to discriminate in neighborhoods with more ethnic presence.     

Impact of low fertility and early age at sterilisation on women’s formal education and skill development in South India

This paper examines the impact of low fertility and early age at sterilisation on women’s formal education and skill development in South India. Multilevel ordered-logit modelling of pseudo-cohort data re-organised from the three rounds of National Family Health Survey, and thematic analysis of qualitative data collected from Tamil Nadu and Kerala states showed no evidence of women’s resumption of formal education or uptake of skill development training in the post-sterilisation and post-childcare period. While resuming formal education in the post-sterilisation and post-childcare period is harder to achieve for various individual, household, community and policy reasons, there is greater preparedness and support for women to undertake skill development training. As low fertility and early age at sterilisation are widely regarded as the emerging reproductive norm in India, post-sterilisation and -childcare women will be a significant population group both in number and in proportional terms. No government policies or programs have so far recognised this group. India’s new government should consider targeted skill development programs for post-sterilisation and -childcare women appropriate to their social, economic and educational levels. An important contribution of the family planning program, particularly female sterilisation, for the economic and social development of the family and the wider society will otherwise be lost.     

Postmigration Living Difficulties,Help-Seeking and Community Resilience in the Initial Stages of Migration: Coproducing Community Practice with Recent Irish Migrants to London

This article describes a community-based participatory action research (CBPAR) project that examined the postmigration living difficulties (PMLD), help-seeking and community resilience of recent Irish migrants to London (n = 176). The majority of respondents were young adults, in managerial or professional occupations and in good or very good health. Mixed methods indicate inadequate planning for relocation and poor social support as the main difficulties in the initial stages of migration. Community factors promoting resilience included employment opportunities, local and transnational supports, and cultural familiarity and acceptance. Community participation in the action orientated phase of this CBPAR is discussed.     

Signal extraction goodness-of-fit diagnostic tests under model parameter uncertainty: Formulations and empirical evaluation

We present a time-domain goodness-of-fit (gof) diagnostic test that is based on signal-extraction variances for nonstationary time series. This diagnostic test extends the time-domain gof statistic of Maravall (2003 Maravall, A. (2003). A class of diagnostics in the ARIMA-model-based decomposition of a time series. Memorandum, Bank of Spain. Available at http://www.bde.es/servicio/software/tramo/diagnosticsamb.pdf [Google Scholar]) by taking into account the effects of model parameter uncertainty, utilizing theoretical results of McElroy and Holan (2009 McElroy, T., Holan, S. (2009). A local spectral approach for assessing time series model misspeci?cation. Journal of Multivariate Analysis 100:604–621.[Crossref], [Web of Science ®] , [Google Scholar]). We demonstrate that omitting this correction results in a severely undersized statistic. Adequate size and power are obtained in Monte Carlo studies for fairly short time series (10 to 15 years of monthly data). Our Monte Carlo studies of finite sample size and power consider different combinations of both signal and noise components using seasonal, trend, and irregular component models obtained via canonical decomposition. Details of the implementation appropriate for SARIMA models are given. We apply the gof diagnostic test statistics to several U.S. Census Bureau time series. The results generally corroborate the output of the automatic model selection procedure of the X-12-ARIMA software, which in contrast to our diagnostic test statistic does not involve hypothesis testing. We conclude that these diagnostic test statistics are a useful supplementary model-checking tool for practitioners engaged in the task of model-based seasonal adjustment.     

‘You Feel It in Your Body’: How Australian Children and Young People Think about and Experience Feeling and Being Safe

In 2012, the Australian Government announced the establishment of a Royal Commission into Institutional Responses to Child Sexual Abuse. The aim of the Royal Commission is to understand how and why sexual abuse occurred within Australian institutions and to provide guidance as to how future abuse might be prevented. The Royal Commission commissioned a mixed methods study to explore what children need to be safe and to feel safe, to explore how they determine their level of safety, and their observations about how institutions act to prevent and respond to safety issues. This article reports on the findings from the first phase of the study that involved focus groups carried out with children aged 4–17 years from different types of institutions. The discussion focused particularly on how children conceptualise safety and how they make judgments about their levels of safety. Children and young people's conceptualisation of safety had multiple dimensions, which include the idea that being safe and feeling safe are two distinct, interrelated but sometimes non‐concurrent experiences; that safety is identified and experienced as a set of feelings; trusting relationships are the foundation of safety; familiarity helps children feel safe; and safe environments are those that are ordered and orderly.     

On the Road to Resilience: The Help‐Seeking Experiences of Irish Emigrant Survivors of Institutional Abuse

Understanding how survivors of complex trauma navigate towards resources can inform the design of interventions and health promotion strategies. However, there are little data on the resilience and help‐seeking experiences of this group or others who have experienced institutional abuse in childhood. This empirical study sets out to illustrate the help‐seeking experiences of Irish emigrant survivors of institutional childhood abuse (ICA). Twenty‐two survivors of ICA were purposefully recruited from community organisations in the UK and data were collected via semi‐structured interviews. As a result of negative initial help‐seeking experiences in Ireland, most participants engaged in long periods of self‐management and disclosed information about their childhood as part of a redress scheme in later life. Outside of this scheme, turning points, such as illness or family problems, and the needs of children were influential in seeking help. Peer support networks played an important role as a trusted signposting pathway towards formal interventions. Participants identified interpersonal barriers to formal help‐seeking as helping professionals' failure to share control, insensitivity to identity loss and literacy issues, and the lack of explicit boundaries. The paper concludes with a discussion about the implications for research and future practice.

‘This empirical study sets out to illustrate the help‐seeking experiences of Irish emigrant survivors of institutional childhood abuse’

Key Practitioner Messages:

• Turning points, such as illness and bereavement, and the desire to provide for children, influence the help‐seeking of survivors of ICA.
• Irish emigrant survivors of ICA cite failure to share control, insensitivity to identity loss, literacy issues and the lack of explicit boundaries as barriers to help‐seeking.
• General awareness of ICA can help practitioners in low‐threshold services prevent against culturally insensitive practice.
• Peer support networks can provide uniquely trusted signposting towards formal interventions.

     

Gendered experiences of physical restraint on locked wards for women

Physical restraint is used in inpatient services for people with intellectual disabilities as a way of holding a person to avoid injury. This article uses data from an ethnographic study in a locked unit in the north of England to explore women’s experiences of physical restraint using a feminist disability studies analysis. Data consists of field notes as well as interviews with 16 of the women who had experienced restraint, and 10 staff who worked with them. The women gave insights into the gendered phenomenon of restraint in light of their past experiences of violence. The authors argue that restraint is used with women to encourage passivity at times when more relational and therapeutic methods could be used. The article offers recommendations for alternative strategies that services can encourage.     

Care in a Time of Austerity: the Electronic Monitoring of Homecare Workers’ Time

Austerity places intense pressures on labour costs in paid care. In the UK, electronic monitoring technology has been introduced to record (and materially reduce) the working time and wages of homecare workers. Based on empirical findings, we show that, in a ‘time of austerity’, care is reductively constructed as a consumption of time. Service users are constructed as needy, greedy, time‐consumers and homecare workers as resource‐wasting time‐takers. We point to austerity as a temporal ideology aimed at persuading populations that individual deprivation in the present moment, self‐sacrifice and the suppression of personal need in the here and now is a necessary requirement to underpin a more secure national future. Accordingly, women in low‐waged care work are required to eschew a rights‐bearing, present‐tense identity and are assumed willing to suppress their entitlements to lawful wages as a sacrifice to the future. By transforming our understandings of ‘care’ into those of ‘time consumption’, and by emphasizing the virtue of present‐tense deprivation, a politics of austerity appears to justify time‐monitoring in care provision and the rationing of homecare workers’ pay.