Ecological Bias: Use of Maximum-Entropy Approximations

The focus of geographical studies in epidemiology has recently moved towards looking for effects of exposures based on data taken at local levels of aggregation (i.e. small areas). This paper investigates how regression coefficients measuring covariate effects at the point level are modified under aggregation. Changing the level of aggregation can lead to completely different conclusions about exposure–effect relationships, a phenomenon often referred to as ecological bias. With partial knowledge of the within‐area distribution of the exposure variable, the notion of maximum entropy can be used to approximate that part of the distribution that is unknown. From the approximation, an expression for the ecological bias is obtained; simulations and an example show that the maximum‐entropy approximation is often better than other commonly used approximations.     

Likelihood-based estimation for Gaussian MRFs

Markov random fields (MRFs) express spatial dependence through conditional distributions, although their stochastic behavior is defined by their joint distribution. These joint distributions are typically difficult to obtain in closed form, the problem being a normalizing constant that is a function of unknown parameters. The Gaussian MRF (or conditional autoregressive model) is one case where the normalizing constant is available in closed form; however, when sample sizes are moderate to large (thousands to tens of thousands), and beyond, its computation can be problematic. Because the conditional autoregressive (CAR) model is often used for spatial-data modeling, we develop likelihood-inference methodology for this model in situations where the sample size is too large for its normalizing constant to be computed directly. In particular, we use simulation methodology to obtain maximum likelihood estimators of mean, variance, and spatial-depencence parameters (including their asymptotic variances and covariances) of CAR models.     

Estimation of the Intraclass Correlation Coefficient for the Analysis of Covariance Model

For the unbalanced analysis of covariance model with one covariate, a simple formula is given for the intraclass correlation coefficient estimator that results from Henderson's Method 3 estimation of variance components. Example calculations and the corresponding interpretations are given for a study of the correlation of iron content among brothers. The example illustrates the manner in which the estimator depends on the pattern of correlation between the covariate and the variable under investigation.     

Asymptotics for REML estimation of spatial covariance parameters

In agricultural field trials, restricted maximum likelihood estimation (REML) of the spatial covariance parameters is often preferred to maximum likelihood. Although it has either been conjectured or assumed that REML estimators are asymptotically Gaussian, conditions under which such asymptotic results hold are clearly needed. This article gives checkable conditions for spatial regression when sampling locations are either on a rectangular grid or are irregularly spaced but satisfy certain growth conditions.     

A few statistical principles for data science

In any other circumstance, it might make sense to define the extent of the terrain (Data Science) first, and then locate and describe the landmarks (Principles). But this data revolution we are experiencing defies a cadastral survey. Areas are continually being annexed into Data Science. For example, biometrics was traditionally statistics for agriculture in all its forms but now, in Data Science, it means the study of characteristics that can be used to identify an individual. Examples of non-intrusive measurements include height, weight, fingerprints, retina scan, voice, photograph/video (facial landmarks and facial expressions) and gait. A multivariate analysis of such data would be a complex project for a statistician, but a software engineer might appear to have no trouble with it at all. In any applied-statistics project, the statistician worries about uncertainty and quantifies it by modelling data as realisations generated from a probability space. Another approach to uncertainty quantification is to find similar data sets, and then use the variability of results between these data sets to capture the uncertainty. Both approaches allow ‘error bars’ to be put on estimates obtained from the original data set, although the interpretations are different. A third approach, that concentrates on giving a single answer and gives up on uncertainty quantification, could be considered as Data Engineering, although it has staked a claim in the Data Science terrain. This article presents a few (actually nine) statistical principles for data scientists that have helped me, and continue to help me, when I work on complex interdisciplinary projects.     

Conversion Ratios, Efficiency and Obfuscation: A Study of the Impact of Changed UK Charity Accounting Requirements on External Stakeholders

Key stakeholders in the UK charity sector have, in recent years, advocated greater accountability for charity performance. Part of that debate has focussed on the use of conversion ratios as indicators of efficiency, with importance to stakeholders being contrasted with charities’ apparent reluctance to report such measures. Whilst, before 2005, conversion ratios could have been computed from financial statements, changes in the UK charity SORP have radically altered the ability of users to do this. This article explores the impact on the visibility of such information through an analysis of the financial statements of large UK charities before and after the 2005 changes. Overall, the findings suggest that, despite the stated intention of increasing transparency in respect of charity costs, the application of the changes has resulted in charities ‘managing’ the numbers and limiting their disclosures, possibly to the detriment of external stakeholders.     

Breaking the in‐group out‐group: shifting boundaries in transnational partner choice processes of individuals of Moroccan,Tunisian, Algerian,Turkish, Punjabi Sikh,Pakistani and Albanian descent in Belgium

The ongoing popularity in some second and third generation migrants in Western Europe of marrying a partner from the countries of origin of their (grand)parents is considered to be problematic for micro and macro level societal integration of some migrant populations. Partner choice and marriage practices in migrant communities are problematized in public, media and political discourses by discriminating them from marriage practices in the ‘native’ population on the basis of three related dichotomies: (1) agency versus structure, (2) us versus them and (3) romantic versus instrumental marriage intentions dichotomies. By means of in‐depth qualitative research methodologies on the partner choice processes of women and men of Turkish, Moroccan, Algerian, Tunisian, Punjabi Sikh, Pakistani and Albanian descent in Belgium and an intersectional theoretical approach, this article aims to deconstruct popular and simplifying dichotomous representations of partner choice processes in these migrant populations. Our study reveals how religious, gender and social class boundaries are stretched to meet personal/individual desires and preferences. Individuals do experience social restrictions when it concerns social group boundaries and the potential partners that they can look for. At the same time individuals are never fully determined by their social environment, they creatively develop strategies to by‐pass certain restrictions and to some extent are able to meet their personal needs while being sensitive to the desires of their social environment.     

Regimes of Mobility Across the Globe

Mobility studies emerged from a postmodern moment in which global ‘flows’ of capital, people and objects were increasingly noted and celebrated. Within this new scholarship, categories of migrancy are all seen through the same analytical lens. This article and Regimes of Mobility: Imaginaries and Relationalities of Power, the special issue of JEMS it introduces, build on, as well as critique, past and present studies of mobility. In so doing, this issue challenges conceptual orientations built on binaries of difference that have impeded analyses of the interrelationship between mobility and stasis. These include methodological nationalism, which counterpoises concepts of internal and international movement and native and foreigner, and consequently normalises stasis. Instead, the issue offers a regimes of mobility framework that addresses the relationships between mobility and immobility, localisation and transnational connection, experiences and imaginaries of migration, and rootedness and cosmopolitan openness. The introduction highlights how, within this framework and its emphasis on social fields of differential power, the contributors to this collection ethnographically explore the disparities, inequalities, racialised representations and national mythscapes that facilitate and legitimate differential mobility and fixity. Although the authors examine nation-state building processes, their analysis is not confined by national boundaries.     

Overt and Relational Aggression Participant Role Behavior: Measurement and Relations With Sociometric Status and Depression

This study is the first to measure participant role behavior across overt and relational forms of aggression. The Overt and Relational Aggression Participant Role Behavior Scales were designed to measure aggression, assisting, reinforcing, defending, victimization, and outsider behavior during acts of peer aggression in an ethnically diverse sample of 609 adolescents (M age = 12 years). The data fit the hypothesized 12‐factor model, and measurement invariance was established across gender. Relational victimization, but not overt victimization, was positively associated with all other relational aggression roles. Each participant role subscale was positively associated with depressive symptoms with the exception of the overt and relational outsider subscales. Future research and intervention efforts should consider overt and relational aggression participant roles, separately.