Sequential change detection in the presence of unknown parameters

It is commonly required to detect change points in sequences of random variables. In the most difficult setting of this problem, change detection must be performed sequentially with new observations being constantly received over time. Further, the parameters of both the pre- and post- change distributions may be unknown. In Hawkins and Zamba (Technometrics 47(2):164–173, 2005), the sequential generalised likelihood ratio test was introduced for detecting changes in this context, under the assumption that the observations follow a Gaussian distribution. However, we show that the asymptotic approximation used in their test statistic leads to it being conservative even when a large numbers of observations is available. We propose an improved procedure which is more efficient, in the sense of detecting changes faster, in all situations. We also show that similar issues arise in other parametric change detection contexts, which we illustrate by introducing a novel monitoring procedure for sequences of Exponentially distributed random variable, which is an important topic in time-to-failure modelling.     

Calibration of FISK, an Invasiveness Screening Tool for Nonnative Freshwater Fishes

Adapted from the weed risk assessment (WRA) of Pheloung, Williams, and Halloy, the fish invasiveness scoring kit (FISK) was proposed as a screening tool for freshwater fishes. This article describes improvements to FISK, in particular the incorporation of confidence (certainty/uncertainty) ranking of the assessors' responses, and reports on the calibration of the score system, specifically: determination of most appropriate score thresholds for classifying nonnative species into low-, medium-, and high-risk categories, assessment of the patterns of assessors' confidences in their responses in the FISK assessments. Using receiver operating characteristic (ROC) curves, FISK was demonstrated to distinguish accurately (and with statistical confidence) between potentially invasive and noninvasive species of nonnative fishes, with the statistically appropriate threshold score for high-risk species scores being ≥19. Within the group of species classed as high risk using this new threshold, a "higher risk" category could be visually identified, at present consisting of two species (topmouth gudgeon Pseudorasbora parva and gibel carp Carassius gibelio ). FISK represents a useful and viable tool to aid decision- and policymakers in assessing and classifying freshwater fishes according to their potential invasiveness.     

Poverty,Government Policy and Public Opinion in Britain and Israel: A Comparative Analysis

What are the effects of public opinion on social welfare policies? To what extent is increased financial strain associated with stronger support for anti‐poverty policies? This article tests welfare state theory by comparing poverty, government policy and public opinion on poverty in the UK and Israel, based on rich and detailed comparable survey data on the conditions of the poor in both countries. The results show that, despite similar levels of income poverty and inequality, the poor have a considerably lower standard of living in Israel than the UK. There is considerably greater public support for the poor in Israel but limited government action to end poverty, whereas in the UK there is more limited public support for the poor but significant government action on poverty and exclusion. In both countries there appears to be only a limited connection between social solidarity with the poor and the political elite's rhetoric and action.     

The vanishing physician scientist: a critical review and analysis

Review of the concept of "the vanishing physician-scientist" shows: 1) medical school admissions reject most students wanting medical research careers; 2) college years before medical school are the best time for students to begin research; 3) efforts to entice admitted medical students and residents to do research are too little too late, yielding people not equipped to compete for grants with PhD track peers and less motivated because they have clinical careers to fall back on; 4) the MD/PhD could be replaced by the PhD/MD with uninterrupted research: a full PhD in parallel with part-time medical school followed by part-time residencies. Supplemental materials are available for this article. Go to the publisher's online edition of Accountability in Research to view the free supplemental file.     

The impact of health insurance cost-sharing method on healthcare utilisation in China

In current Chinese health insurance programmes, there are two types of cost-sharing methods: the time-of-service copayment policy and the reimbursement policy. In contrast to the copayment participants, reimbursement participants need to pay for all medical expenses in advance. We study the effect of the reimbursement policy on the utilisation of healthcare services in China. The theoretical analysis indicates that the medical consumption of low income households will be less than the optimal consumption level when enrolled in a reimbursement programme instead of a copayment programme. Empirically, using data from the China Health and Retirement Longitudinal Study (CHARLS), we find that the total inpatient expenditure of the reimbursement participants is 12.7% lower than that of copayment enrolees, and the reimbursement arrangement negatively impacts low-income and rural populations. Therefore, reimbursement participants, those who are financially constrained, are more likely to suffer the up-front payment burden and finally reduce their healthcare needs.     

Nonparametric estimation of multivariate extreme-value copulas

Extreme-value copulas arise in the asymptotic theory for componentwise maxima of independent random samples. An extreme-value copula is determined by its Pickands dependence function, which is a function on the unit simplex subject to certain shape constraints that arise from an integral transform of an underlying measure called spectral measure. Multivariate extensions are provided of certain rank-based nonparametric estimators of the Pickands dependence function. The shape constraint that the estimator should itself be a Pickands dependence function is enforced by replacing an initial estimator by its best least-squares approximation in the set of Pickands dependence functions having a discrete spectral measure supported on a sufficiently fine grid. Weak convergence of the standardized estimators is demonstrated and the finite-sample performance of the estimators is investigated by means of a simulation experiment.     

COMMUNITY COHESION,ASYLUM SEEKING AND THE QUESTION OF THE ‘STRANGER’

This paper addresses the changing governance of the social through the conjunction of international, national and local strategies where attempts to regulate migration and promote community safety meet. Migration has been increasingly subjected to processes of ‘securitization’ and ‘criminalization’ that encounter and align with new pressures in ‘domestic’ crime and safety policies. The paper offers a critical evaluation of the sociological grand narratives that frame these events, arguing instead for a more nuanced analysis of the instabilities and volatilities of governance strategies and practices – and the normative issues that they bring into view.     

Toward a Social Work Frame of Reference

Social workers are looking for workable yet exact methods to evaluate practice. Intensive single-case experimental designs have been proposed as promising methods for bridging the research-practice chasm. The application of these designs, however, may compromise practice and generate inconclusive research. Additionally, social workers are unlikely to use such designs because of their discontinuity with current practice methods. A continuum of alternative practice evaluation methods is drawn. Rudimentary ideographic designs are described and proposed for inclusion in social work education to stimulate research interest, perspective, and skill.     

Cultural Competency as New Racism: An Ontology of Forgetting

This article argues that cultural competency promotes an obsolete view of culture and is a form of new racism. Cultural competency resembles new racism both by otherizing non-whites and by deploying modernist and absolutist views of culture while not using racialist language. Drawing on child welfare, cultural competence is shown to repeat what Lowe (1993) calls an ontology of forgetting Canada's history of colonialism and racism. A recommendation is made for jettisoning cultural competency and emphasizing instead a self-reflexive grappling with racism and colonialism.     

On the Front Lines: The Voices and Experiences of Racialized Child Welfare Workers in Toronto,Canada

Drawing on focus group data highlighting the perceptions and experiences of racialized child protection workers in the Greater Toronto Area, this article explores the ways in which race operates in the Ontario child welfare system. Most study participants experienced the agencies in which they worked as White-normed environments characterized by systemic racial discrimination in promotion and advancement as well as ongoing instances of racial microaggression—common, everyday practices that denigrate people of color. Several participants spoke of having to contend with White-normed and middle-class-oriented policies, tools, and practices that often prevented them from meeting the unique needs of racialized service users. The article concludes with participants' recommendations for creating a more equitable child welfare system.