The peculiar shrinkage properties of partial least squares regression

Partial least squares regression has been widely adopted within some areas as a useful alternative to ordinary least squares regression in the manner of other shrinkage methods such as principal components regression and ridge regression. In this paper we examine the nature of this shrinkage and demonstrate that partial least squares regression exhibits some undesirable properties.     

DEMAND/WITHDRAW INTERACTION PATTERNS BETWEEN DIFFERENT TYPES OF BATTERERS AND THEIR SPOUSES

The investigation of subtypes of violent men could provide invaluable information to researchers and clinicians. In earlier studies, investigators examined whether subtypes of male batterers could be identified based on physiological markers in combination with observational and self-report perspectives. In a sample of batterers and their wives, they found a physiological marker that discriminated between two groups of violent men on several interesting dimensions. To highlight the importance of studying batterer typologies, the present study examined differences in marital interaction patterns across the two groups of batterers. Analyses revealed clinically relevant patterns of interaction in the two groups, and effect sizes indicating the possibility of differences between the two types of batterers. Implications for future research as well as therapy are discussed.     

Foxing the nation: the economic (in)significance of hunting with hounds in Britain

The election in 1997 of a new Labour Government and the publication of the Wild Mammals (Hunting With Dogs) Bill provided an opportunity for the re-opening of the public and political debate about hunting wild animals with hounds in Britain. A significant new dimension to the 1997/98 debate was the increasing emphasis on the claimed economic importance of hunting and its provision of rural jobs. This paper critically examines the nature of such claims. It argues that economic claims about hunting should be assessed in the context of a changing rural economy, and demonstrates how the pro-hunting lobby's predictions of job losses from banning hunting are difficult to sustain. It suggests that if our starting point is a concern for the rural economy, then hunting is a minor issue compared with other pressing issues of the late 1990s such as, for example, European rural policy reforms. Moreover, a wider economic analysis suggests that hunting wild mammals imposes other social costs, in the form of disruption and damage to property, which could be avoided by switching to non-quarry hunts. The paper concludes by examining the reasons for the rise of this economic dimension to the hunting debate.     

War Leaves an Enduring Legacy in Combatants’ Lives

The memory of combat experience endures in World War II veterans. As veterans age, traumatic memory that previously may have been suppressed in the busyness of family and everyday life can re-emerge. Combat stress may affect not only the veterans, but also those people closely associated with them. Interviews were conducted with World War II veteran aircrew, wives, children, grandchildren, siblings, and friends to examine the impact of combat experience on the veterans and the family across the life course from the perspectives of the various participants. The combat experience significantly affected the life course of most.     

A Tale of Two Counties: Natives’ Opinions Toward Immigration in North Carolina1

This article compares native residents’ opinions and perceptions regarding immigration using a representative survey from a pair of matched North Carolina counties – one that experienced recent growth of its foreign-born population and one that did not. Drawing from several theoretical perspectives, including group threat, contact theory, and symbolic politics, we formulate and empirically evaluate several hypotheses. Results provide limited evidence that competition and threat influence formation of opinions about immigration, with modest support for claims that parents with school-aged children harbor more negative views of immigration than their childless counterparts. Except for residents in precarious economic situations, these negative opinions appear unrelated to the immigrant composition of the community. Claims that the media promotes negative views of immigration receive limited support, but this relationship is unrelated to the volume of local immigration. Finally, sustained contacts with foreign-born residents outside work environments are associated with positive views of immigration, but superficial contacts appear to be conducive to anti-immigration sentiments. Political orientation, educational attainment, and indicators of respondents’ tolerance for diversity explain most of the difference between the two counties in overall support for immigration.     

Social work in mental health services: A survey of the field

Abstract

A survey of social workers employed in mental health services was conducted in Victoria in mid-1997. Approximately 300 social workers were identified as working in the sector. About half were employed in adult clinical services, 23% in psychiatric disability services, 12.4% in Child and Adolescent Mental Health Services, and the rest in a range of other services. More than 90% worked in a community based service or team. The number of entry-level (SW I) positions in clinical services was found to have declined over the last ten years from 61 to 14, resulting in a lack of opportunities for social workers to gain experience in base grade positions, and difficulty in recruiting to SW II positions. Major issues of concern reported by social workers included: the lack of accommodation and other community resources for consumers; diminished opportunities for professional development, supervision, and discipline-specific training; lack of professional recognition; increasing workloads; and organisational emphasis on throughput rather than quality.     

Lessons from Nigeria for improved thinking and working politically in the extractives sector

Despite the wealth that comes from being the biggest oil producer in Africa, Nigeria has some of the worst development indicators in the world. From 2011 to mid‐2016, the DFID‐funded Facility for Oil Sector Transparency and Reform (FOSTER) programme's unique design aimed to reduce incentives for the capture of oil revenue by elites and international oil companies, restoring the potential of those revenues to accelerate economic and social development. This article asks what lessons FOSTER's successes and failures offer for improved “thinking and working politically” (TWP). It examines the outcomes from five “clusters” of interventions: three viewed by the FOSTER team as successes and two as failures. The article identifies factors for successful TWP‐based programming, including the need for local ownership rooted in staff with a combination of technical expertise, a deep knowledge of the local political context and excellent networking abilities. The research used a qualitative and inductive approach. Field research was undertaken with 44 semi‐structured qualitative interviews during one month of fieldwork in Abuja and Lagos. The research also included reviews of FOSTER's internal documentation and evaluation frameworks, as well as analysis of newspaper articles and grey literature on the oil sector in Nigeria. The project offers important lessons for politically informed programming about how interventions were implemented (process), what was actually done (content) and how the project responded to changes in context that created or blocked opportunities for reform (responsiveness). The article identifies factors for successful TWP‐based programming, including the need for local ownership rooted in staff with a combination of technical expertise, a deep knowledge of the local political context and excellent networking abilities. The findings have important implications for programme design. They demonstrate the value of built‐in flexibility that allows staff to choose and switch the partners they work with and the channels they work through. They also show that a key aspect of TWP‐based programming is implicit acceptance that some failure may be unavoidable, since this permits staff to balance risk against opportunities. Finally, a better understanding of FOSTER's failures reveals the challenges of a TWP‐based approach and the trade‐offs it demands.     

A frequency domain comparison of estimation methods for gaussian fields

This paper demonstrates that well-known parameter estimation methods for Gaussian fields place different emphasis on the high and low frequency components of the data. As a consequence, the relative importance of the frequencies under the objective of the analysis should be taken into account when selecting an estimation method, in addition to other considerations such as statistical and computational efficiency. The paper also shows that when noise is added to the Gaussian field, maximum pseudolikelihood automatically sets the smoothing parameter of the model equal to one. A simulation study then indicates that generalised cross-validation is more robust than maximum likelihood un-

der model misspecification in smoothing and image restoration problems. This has implications for Bayesian procedures since these use the same weightings of the frequencies as the likelihood.