Models for longitudinal data with censored changepoints

Summary.  In longitudinal studies of biological markers, different individuals may have different underlying patterns of response. In some applications, a subset of individuals experiences latent events, causing an instantaneous change in the level or slope of the marker trajectory. The paper presents a general mixture of hierarchical longitudinal models for serial biomarkers. Interest centres both on the time of the event and on levels of the biomarker before and after the event. In observational studies where marker series are incomplete, the latent event can be modelled by a survival distribution. Risk factors for the occurrence of the event can be investigated by including covariates in the survival distribution. A combination of Gibbs, Metropolis–Hastings and reversible jump Markov chain Monte Carlo sampling is used to fit the models to serial measurements of forced expiratory volume from lung transplant recipients.     

Research with Disabled Children: How Useful is Child-centred Ethics?

The title of a collection on 'ethics and methodology of research with children' implies that research with children necessarily raises unique questions about ethics and methods. Our paper questions whether this is so, what the unique questions might be and how they arise. We consider that any extra complications in research with children are common to research with other 'minority' groups. The main complications do not arise from children's inabilities or misperceptions, but from the positions ascribed to children in late twentieth-century Western societies. Clarity about the social origins of any complications in research with children is crucial if these complications are to be addressed. Ethics, methods, theories, data and policy conclusions are inextricably interwoven, and it is important to acknowledge how initial theories inevitably shape policies. Reasons are given for preferring rights-based to child-centred ethics.     

Public expenditure in the UK: how measures matter

Summary.  Studying spending over time requires reliable data. It is not clear that such data exist in the UK, however. The two published sources of functional spending numbers—the Office for National Statistics's 'blue book' and Her Majesty's Treasury's Public Expenditure Statistical Analyses (PESA)—rely on estimates of past spending, using a link year method, rather than recalculating actual spending figures when functional definitions change. We assess the various measures of spending in the UK. Specifically, we do two things. First, we present a new, third, set of spending numbers applying temporally consistent functional definitions to PESA microdata. Second, we compare the three measures. Our analyses indicate that the Office for National Statistics and PESA data differ quite markedly, especially for certain functions, i.e. in some cases the two measures imply completely different histories. The differences between the original PESA data and our new measures are less pronounced on average, though significant differences are evident, especially year by year.     

Model-free variable selection

Summary.  The importance of variable selection in regression has grown in recent years as computing power has encouraged the modelling of data sets of ever-increasing size. Data mining applications in finance, marketing and bioinformatics are obvious examples. A limitation of nearly all existing variable selection methods is the need to specify the correct model before selection. When the number of predictors is large, model formulation and validation can be difficult or even infeasible. On the basis of the theory of sufficient dimension reduction, we propose a new class of model-free variable selection approaches. The methods proposed assume no model of any form, require no nonparametric smoothing and allow for general predictor effects. The efficacy of the methods proposed is demonstrated via simulation, and an empirical example is given.     

De-Unionization and macro performance: What Freeman and Medoff didn’t do

Most, if not all, unions have monopoly power, which they can use to raise wages above competitive levels.-Freeman and Medoff (1984: 6) The inequality of bargaining power between employees who do not possess full freedom of association or actual liberty of contract and employers who are organized in the corporate or other forms of ownership association substantially burdens and affects the flow of commerce, and tends to aggravate recurrent business depressions, by depressing wage rates and the purchasing power of wage earners in industry and by preventing the stabilization of competitive wage rates and working conditions within and between industries.-Preamble to the Wagner Act of 1935     

Relationship between news media coverage of medical research and academic medical centers and people volunteering for clinical trials

In academic medical centers an untested assumption is that positive media attention aids recruitment of patients into a medical study while negative news reporting is damaging. In this study we examine associations between the amount of newspaper coverage concerning medical research and the number of people who volunteer, and the positive or negative content of the reporting. We find evidence that a positive relationship, though not statistically significant, exists between the volume of media coverage and volunteerism; a positive relationship exists between positive media coverage and volunteerism; and no existence of an inverse relationship between negative news coverage and volunteerism. These results lay a foundation for more in-depth exploration into the role news media play in this type of volunteerism.     

The use of alternative work arrangements by the jobless: Evidence from the CAEAS/CPS

Alternative work arrangements (AWAs), such as contracting, consulting, and temporary work, have been criticized as providing only atypical, even precarious, employment. Yet they may also allow workers to locate suitable job matches. Exploiting data from four Contingent and Alternative Employment Arrangement Supplements to the Current Population Survey, we investigate the initial job-finding strategies pursued by the unemployed. Within the narrow window offered by the data, we find that unemployed workers who become reemployed are more likely to find work in AWAs than in regular, open-ended employment. When we evaluate the use of AWAs against unemployment, there is also evidence that the jobless are entering AWAs as pathways out of their initial labor market state.     

Inference for clusters of extreme values

Summary. Inference for clusters of extreme values of a time series typically requires the identification of independent clusters of exceedances over a high threshold. The choice of declustering scheme often has a significant effect on estimates of cluster characteristics. We propose an automatic declustering scheme that is justified by an asymptotic result for the times between threshold exceedances. The scheme relies on the extremal index, which we show may be estimated before declustering, and supports a bootstrap procedure for assessing the variability of estimates.     

Rescuing from oblivion: social characteristics and career destinations of early British ‘sociology’ graduates, 1907–39

Those students who were among the first sociology graduates in the UK barely feature in standard histories of the discipline, which all have an intellectual and institutional focus. This article remedies this neglect by researching the social backgrounds and later careers of sociology graduates from the London School of Economics and Political Science [LSE] and Bedford College for Women from the first such graduate in 1907 until those graduating in the 1930s. Data for this exercise were compiled from a variety of sources. The more important are: UK censuses, especially that of 1911; various civil registration records; archived student files; and, for the graduates who entered university teaching, issues of the Yearbook of the Universities of the Empire [later the Commonwealth Universities' Yearbook]. The dataset includes all identified graduates in the BSc(Econ), Special Subject Sociology, degree from 1907 to 1935 and all in the BA (Honours) in Sociology degree from 1925 to 1939. LSE sociology graduates tended to be older and to have more cosmopolitan backgrounds, with fathers more likely than for Bedford College graduates to come from commercial rather than professional backgrounds. Both institutions' graduates' careers tended to the Civil Service and local government. LSE graduates gravitated to education, especially to higher education if male, whilst those of Bedford College went into welfare work, countering a stereotype from some previous literature that especially women graduates were heavily constrained to follow careers in schoolteaching. The article also gives comparisons with the social‐class profile and career destinations of several cohorts of postwar sociology graduates, noting a number of similarities.