Inference in model-based cluster analysis

A new approach to cluster analysis has been introduced based on parsimonious geometric modelling of the within-group covariance matrices in a mixture of multivariate normal distributions, using hierarchical agglomeration and iterative relocation. It works well and is widely used via the MCLUST software available in S-PLUS and StatLib. However, it has several limitations: there is no assessment of the uncertainty about the classification, the partition can be suboptimal, parameter estimates are biased, the shape matrix has to be specified by the user, prior group probabilities are assumed to be equal, the method for choosing the number of groups is based on a crude approximation, and no formal way of choosing between the various possible models is included. Here, we propose a new approach which overcomes all these difficulties. It consists of exact Bayesian inference via Gibbs sampling, and the calculation of Bayes factors (for choosing the model and the number of groups) from the output using the Laplace–Metropolis estimator. It works well in several real and simulated examples.     

Inventing adulthoods: a biographical approach to understanding youth citizenship

Traditionally adulthood and citizenship have been synonymous. Yet adulthood is changing. In this paper we explore how young people's evolving understandings of adulthood may contribute towards an understanding of citizenship within the broader context of increasingly extended and fragmented transitions. The paper draws on a unique qualitative longitudinal data set in which 100 young people, from contrasting social backgrounds in the United Kingdom, have been followed over a five‐year period using repeat biographical interviews. We present first the themes that emerged from a cross‐cut analysis of the first of three rounds of interviews distinguishing between relational and individualised understandings of adulthood. We then present a model we developed to capture the ways that young people sought out opportunities for competence and recognition in different fields of their lives. Finally a case study that follows a young woman through her three interviews illustrates how these themes can appear in an individual trajectory. We offer the model and case study as a way of exploring a more subjective approach to citizenship in which participation is not deferred to some distant future in which economic independence is achieved, but is understood as constantly constructed in the present.     

Labor market flexibility: An index approach to cross-country comparisons

Recently, researchers have used measures of economic freedom (Gwartney and Lawson, 2002) to quantify the relationship between various institutional factors and measures of economic performance. Using a subset of these data, we develop a labor market flexibility index. This measure should be useful to researchers who study labor market performance among countries.     

School-Choice Stories: The Role of Culture

This article uses data from in-depth interviews conducted with the parents of a sample of 88 ninth-grade students from public, private, Catholic, and Christian high schools in two different suburban communities. This research investigates the ways in which parents understand education and how they make sense of schooling options for their children. It shows both how families who choose schools make the selection among various alternatives and why some families seem not to choose schools. This research finds that the financial and information resources of families are not enough in and of themselves to explain school-choice behavior. While these resources are indeed used by families as they make school choices, such measures do not capture the cultural dimension of school choice. In this context culture is understood as the lens through which people make sense of the social world. The decision to activate resources and the direction in which those resources will be activated are mediated by culture. In particular, as these school-choice stories show, the school-choice decision is influenced by the past educational experiences of the parents and by their religious faith.     

Happiness of the very wealthy

The subjective well-being of very wealthy persons was compared with that of a control group who lived in the same geographical area. One hundred persons from Forbes list of wealthiest Americans were queried, as well as 100 control persons selected from telephone directories. The 49 wealthy respondents reported average levels of subjective well-being which were higher than the 62 control group respondents and any subgroup of respondents in a national sample. However, there were unhappy wealthy people and the average level of this group was only modestly higher than for other groups. None of the respondents believed that money is a major source of happiness. When the major sources of happiness mentioned by the two groups were coded for Maslow's needs, it was found that the wealthy group more often mentioned self-esteem and self-actualization and less frequently mentioned physiological and security needs.     

Nonprofit organization financial performance measurement: An evaluation of new and existing financial performance measures

Consensus about financial performance measurement remains elusive for nonprofit organization (NPO) researchers and practitioners alike, due in part to an overall lack of empirical tests of existing and new measures. The purpose of the current study was to explore potential similarities of financial performance measures derived from two sources: current NPO research and key informant interviews with NPO foundation constituencies. The authors examined financial performance measurement ratios with data from fifteen Internal Revenue Service (IRS) Form 990 line items. Using factor analytic techniques, they found three performance factors, each with two associated financial measurement ratios, to be present. They categorized the performance factors as fundraising efficiency, public support, and fiscal performance. This article discusses implications of the findings and future research.