Learning from a lot: Empirical Bayes for high‐dimensional model‐based prediction

Empirical Bayes is a versatile approach to “learn from a lot” in two ways: first, from a large number of variables and, second, from a potentially large amount of prior information, for example, stored in public repositories. We review applications of a variety of empirical Bayes methods to several well‐known model‐based prediction methods, including penalized regression, linear discriminant analysis, and Bayesian models with sparse or dense priors. We discuss “formal” empirical Bayes methods that maximize the marginal likelihood but also more informal approaches based on other data summaries. We contrast empirical Bayes to cross‐validation and full Bayes and discuss hybrid approaches. To study the relation between the quality of an empirical Bayes estimator and p, the number of variables, we consider a simple empirical Bayes estimator in a linear model setting. We argue that empirical Bayes is particularly useful when the prior contains multiple parameters, which model a priori information on variables termed “co‐data”. In particular, we present two novel examples that allow for co‐data: first, a Bayesian spike‐and‐slab setting that facilitates inclusion of multiple co‐data sources and types and, second, a hybrid empirical Bayes–full Bayes ridge regression approach for estimation of the posterior predictive interval.     

The effect of fast and slow decisions on risk taking

We experimentally compare fast and slow decisions in a series of experiments on financial risk taking in three countries involving over 1700 subjects. To manipulate fast and slow decisions, subjects were randomly allocated to responding within 7 seconds (time pressure) or waiting for at least 7 or 20 seconds (time delay) before responding. To control for different effects of time pressure and time delay on measurement noise, we estimate separate parameters for noise and risk preferences within a random utility framework. We find that time pressure increases risk aversion for gains and risk taking for losses compared to time delay, implying that time pressure increases the reflection effect of Prospect Theory. The results for gains are weaker and less robust than the results for losses. We find no significant difference between time pressure and time delay for loss aversion (tested in only one of the experiments). Time delay also leads to less measurement noise than time pressure and unconstrained decisions, and appears to be an effective way of decreasing noise in experiments.     

Religion and the environmental opinion in 22 countries: a comparative study

The objective is to test if religiosity affects environmental opinion in Europe. Using data from European Social Survey (ESS) 2002/2003, the study answers three questions. At the societal level: Is public opinion about the environment different in political systems with different Christian traditions? Is environmental concern less or higher in the public opinion depending on the degree of secularization in the political systems? At the individual level: Is the environmental opinion of the individual affected by the personal confession of faith, religious involvement, and the dominant religious context? At the societal level, the findings show stronger concern for the environment in Catholic and Eastern Orthodox countries than in Protestant countries. The tendency also shows a weakened concern for the environment in countries with a rather secular population. At the individual level, there are significant positive effects on environmental care from Catholic culture, negative effect from Protestant culture, and no effect from religious involvement.     

Research initiation based on idea-circles: from research object to co-actor

This article details an evaluation of a research project based on participatory research methods organized by the Swedish Disability Federation from 2008 to 2011. In Sweden there has been a lack of productive dialogue with the traditional academic world and the question was raised whether proposals for future research would be different if disabled people formulated them. Nine idea-circles with disabled participants and invited researchers from fields of interest close to the participants produced ideas, developed out of the life experience of being a disabled person. These ideas were developed into 72 research drafts that often reflected key advocacy areas, rather than operationalized research issues. The adjustment from the familiar discourse of political struggle to discussion of research was a complicated process for many. When asked to prioritize among areas for research, the representatives from the disability movement chose areas that are not stressed in mainstream disability research in Sweden.     

Organizational closedown and the process of deconstruction and creativity

This paper outlines an analysis of how the deconstruction of organizational, management control and performance management structures affects performances and how workers make sense of enhanced efforts and practices of creativity, in a situation when facing a certainty of job loss as of the closedown of the organization. In this paper, we have shown that the deconstruction of structures generate positive performance outcomes, and that such relation is being mediated by workers identity. We have also shown that identity work under a process of organizational closedown generate certain creativity. By doing so, this paper contributes to the literature on creativity and deconstruction by developing an emergent model where workers identity mediates formal structures in relation to performance. This paper contributes to the literature on closedowns by extending its analytical and theoretical domains, proving alternative, yet complementary and mediating explanations to the causes of drivers to enhanced performances during the process of closedown.     

The psychometric and empirical properties of measures of risk preferences

We examine the psychometric and empirical properties of some commonly used survey-based measures of risk preferences in a population-based sample of 11,000 twins. Using a model that provides a general framework for making inferences about the component of measured risk attitudes that is not due to measurement error, we show that measurement-error adjustment leads to substantially larger estimates of the predictive power of risk attitudes, of the size of the gender gap, and of the magnitude of the sibling correlation. Risk attitudes are predictive of investment decisions, entrepreneurship, and drinking and smoking behaviors; are robustly associated with cognitive ability and personality; and our estimates are often larger than those in the literature. Our results highlight the importance of adjusting for measurement error across a wide range of empirical settings.     

How union mergers affect membership participation

Using data from a survey of union members, we explore how an amalgamation of two Swedish unions affects membership participation. The research literature on the topic is mostly anecdotal and speculative, suggesting that mergers might have detrimental effects on membership participation because they create large unions with centralized governance and administration. But in this study, we do not find a broad-based decline in membership participation measured before and after merger as well as in relation to a comparison union that did not merge. These results are discussed in terms of the national context of union mergers in Sweden and the ways that mergers are negotiated, presented, and implemented to preserve membership participation. An earlier version of this paper was presented at the Third International Conference on Emerging Union Structures: Reshaping Labour Market Institutions, Canberra, Australia in December 1997. The data collection for this project was supported by funds from the National Institute for Working Life in Stockholm.     

Patterns of Informal Help and Caregiving in Sweden: A Thirteen-Year Perspective

This article analyses informal help and caregiving in Sweden with a focus on the scope and trends of change over time. The discussion is based on the results of three national surveys and of one survey conducted in the county of Stockholm. The results indicated that informal help and caregiving was common throughout the period under study. In the 1990s, the figures were fairly stable, while from the late 1990s to 2005 there seems to have been a dramatic increase in the prevalence of such support. Two interpretative perspectives are used to discuss this pattern. One locates its point of departure in recent welfare state changes and in the substitution argument, according to which cuts in welfare services put more pressure on people to provide informal help and care. The second perspective relates to the present debate on civil society and to its possible role in contemporary society. According to the civil society perspective, an increase in the prevalence of informal help and caregiving might be interpreted as an expression of growing civic involvement 'in its own right', without a straightforward and simple relationship to changes in the welfare state. It is argued in the article that the two frames of interpretation should not be viewed as mutually exclusive, but rather that they represent two partly complementary approaches to the understanding of the complex dynamics of unpaid work in contemporary Swedish society.     

Links between informal caregiving and volunteering in Sweden: a 17-year perspective

This article analyses informal caregiving and volunteering in organizations over 17 years in Sweden, with a focus on links between these two forms of unpaid activities. The discussion is based on results from a national survey that was repeated four times in the period 1992–2009. Links were found between the different types of activities. In all four studies a substantial group of the population was involved both in informal caregiving and volunteering. This group of ‘active citizens’ are commonly also engaged in informal social networks. This ‘double active’ group had increased over time and they provide a substantial amount of hours of involvement. Patterns outlined in this article demonstrate that unpaid activities represent a multifaceted phenomenon, and that the boundaries between informal caregiving and volunteering as forms of engagement may be more fluid than has previously been acknowledged. The results challenge the literature in which informal caregiving is viewed as a major obstacle to volunteering. At the same time, however, informal caregiving in general was found to be increasing. There might be reasons to be cautious about the possible risk that too much pressure on citizens for informal caregiving might jeopardize the type of double involvement that is outlined in this article.     

Allodial Land Rights (The Odelsrett) and Early Nineteenth Century Norwegian Nationalism: Propertied Sovereignty as National Sovereignty

The early nineteenth century was a transitional time in western Europe; from the old feudal and imperial order, modern nation states and capitalism emerged. The Norwegian nation state emerged out of the flames of the Napoleonic Wars in 1814. But changes in landed property structures in the eighteenth century lay the ground for Norwegian nationalism in the early nineteenth century. This article explores early nineteenth century nationalism through a focus on property rights and the positive view on the odesrett – an allodial right to land – arguing that an examination of the positive view on the odelsrett can shed new light on Norwegian nationalism in the early nineteenth century. Such an examination suggests that the Norwegian property structure contributed to reinforcing certain property rights element in the Norwegian nationalism where ownership of landed property and national, popular sovereignty were closely interconnected.