Inference in the presence of redundant moment conditions and the impact of government health expenditure on health outcomes in England

In his 1999 article with Breusch, Qian, and Wyhowski in the Journal of Econometrics, Peter Schmidt introduced the concept of “redundant” moment conditions. Such conditions arise when estimation is based on moment conditions that are valid and can be divided into two subsets: one that identifies the parameters and another that provides no further information. Their framework highlights an important concept in the moment-based estimation literature, namely, that not all valid moment conditions need be informative about the parameters of interest. In this article, we demonstrate the empirical relevance of the concept in the context of the impact of government health expenditure on health outcomes in England. Using a simulation study calibrated to this data, we perform a comparative study of the finite performance of inference procedures based on the Generalized Method of Moment (GMM) and info-metric (IM) estimators. The results indicate that the properties of GMM procedures deteriorate as the number of redundant moment conditions increases; in contrast, the IM methods provide reliable point estimators, but the performance of associated inference techniques based on first order asymptotic theory, such as confidence intervals and overidentifying restriction tests, deteriorates as the number of redundant moment conditions increases. However, for IM methods, it is shown that bootstrap procedures can provide reliable inferences; we illustrate such methods when analysing the impact of government health expenditure on health outcomes in England.     

Hierarchical Bayesian level set inversion

The level set approach has proven widely successful in the study of inverse problems for interfaces, since its systematic development in the 1990s. Recently it has been employed in the context of Bayesian inversion, allowing for the quantification of uncertainty within the reconstruction of interfaces. However, the Bayesian approach is very sensitive to the length and amplitude scales in the prior probabilistic model. This paper demonstrates how the scale-sensitivity can be circumvented by means of a hierarchical approach, using a single scalar parameter. Together with careful consideration of the development of algorithms which encode probability measure equivalences as the hierarchical parameter is varied, this leads to well-defined Gibbs-based MCMC methods found by alternating Metropolis–Hastings updates of the level set function and the hierarchical parameter. These methods demonstrably outperform non-hierarchical Bayesian level set methods.     

Tables for computing shortest confidence intervals involving the f-distribution

Tables of multipliers necessary for computing the shortest confidence interval in situations involving the F-distribution are presented. Such situations are illustrated with several examples.     

Investigation of the robustness of two models for assessing synergy in pre‐clinical drug combination studies

Pre‐clinical studies may be used to screen for synergistic combinations of drugs. The types of in vitro assays used for this purpose will depend upon the disease area of interest. In oncology, one frequently used study measures cell line viability: cells placed into wells on a plate are treated with doses of two compounds, and cell viability is assessed from an optical density measurement corrected for blank well values. These measurements are often transformed and analysed as cell survival relative to untreated wells. The monotherapies are assumed to follow the Hill equation with lower and upper asymptotes at 0 and 1, respectively. Additionally, a common variance about the dose–response curve may be assumed. In this paper, we consider two models for incorporating synergy parameters. We investigate the effect of different models of biological variation on the assessment of synergy from both of these models. We show that estimates of the synergy parameters appear to be robust, even when estimates of the other model parameters are biased. Using untransformed measurements provides better coverage of the 95% confidence intervals for the synergy parameters than using transformed measurements, and the requirement to fit the upper asymptote does not cause difficulties. Assuming homoscedastic variances appears to be robust. The added complexity of determining and fitting an appropriate heteroscedastic model does not seem to be justified. Copyright © 2013 John Wiley & Sons, Ltd.     

Changes in racial identification and the educational attainment of American Indians, 1970–1990

We use data from the 1970, 1980, and 1990 census public-use files to assess the impact of newly identified Indians on the educational attainment of American Indians who were at least 25 years old in 1970. We test the hypotheses that this impact was limited to metropolitan areas and to states with small Indian populations. We find that educational attainment for American Indians rose sharply between 1970 and 1990 and that changes in racial identification were an important component of this increase in 1980 but not in 1990. Increases in educational attainment were concentrated in metropolitan areas and occurred in states with large and small Indian populations.     

Suicide and the Creative Class

The tenth leading cause of death in the United States in 2009 was suicide. Emile Durkheim demonstrated that suicide can be studied as a social phenomenon. However, sociologists have been oddly silent on the subject in recent years. Research that has been done by sociologists on suicide has examined the role social capital plays in reducing suicide. However, Richard Florida has argued that today communities are not developing around social capital, but instead moving toward his creative capital model. No study has been done examining the association between creative capital and suicide. This analysis examined what developing around a creative capital model means for suicide. The findings demonstrate that there is a positive association between creative capital and suicide. The current analysis should give pause to communities attempting to develop around the creative capital model.     

Perceptions of Stigmatization and Satisfaction with Services Received,Among Users of Social Welfare Services for the Child and the Family in 3 European Regions

A system of psychosocial indicators, based on atheoretical model describing stigma perceptions byusers and practitioners of social welfare services forchildren and their families, was tested in 3 Europeanregions: Catalonia (Spain), Wales and the Netherlands.Data collection from users included questions on theirsatisfaction with the professional providing theservice and on their involvement in decisions abouthim/her and his/her family. In the Catalan sample oneadditional item asked about satisfaction with theoverall support received.Multiple correspondence analysis showed a consistentpattern of answers for our construct stigmaperceptions, using our indicators system.Discriminant analysis showed that our model works withattributions as expected in 86,32% of cases.Surprisingly, in the discriminant analysis all thesatisfaction indicators were excluded by the stepwisemethod, showing no strong relation between stigmaperception related to a service, and satisfactionusing such a service.Such results suggest that service users clearlydiscriminate between the fact that a service isfunctioning in a stigmatizing way, and the fact theyare satisfied or not with the practitioner helpingthem, with services involving them in decisions, orwith the overall support received from welfareservices.     

<Emphasis Type=Bold>Neighborhoods,Schools, and Academic Achievement: A Formal Mediation Analysis of Contextual Effects on Reading and Mathematics Abilities</Emphasis>

Although evidence indicates that neighborhoods affect educational outcomes, relatively little research has explored the mechanisms thought to mediate these effects. This study investigates whether school poverty mediates the effect of neighborhood context on academic achievement. Specifically, it uses longitudinal data from the Panel Study of Income Dynamics, counterfactual methods, and a value-added modeling strategy to estimate the total, natural direct, and natural indirect effects of exposure to an advantaged rather than disadvantaged neighborhood on reading and mathematics abilities during childhood and adolescence. Contrary to expectations, results indicate that school poverty is not a significant mediator of neighborhood effects during either developmental period. Although moving from a disadvantaged neighborhood to an advantaged neighborhood is estimated to substantially reduce subsequent exposure to school poverty and improve academic achievement, school poverty does not play an important mediating role because even the large differences in school composition linked to differences in neighborhood context appear to have no appreciable effect on achievement. An extensive battery of sensitivity analyses indicates that these results are highly robust to unobserved confounding, alternative model specifications, alternative measures of school context, and measurement error, which suggests that neighborhood effects on academic achievement are largely due to mediating factors unrelated to school poverty.     

The Social Dimensions of Interpersonal Dispute Resolution: A Test of a General Theoretical Framework with Survey Data

Studies of social control most often focus on the deterrent effects of informal or formal social control mechanisms. In this study I draw on theory designed to explain variation in the form of social control itself. Arguing that most social control is exercised in the context of interpersonal disputes, I attempt to explain variation in the form of social control used to resolve disputes. The theoretical model posits that both the social reality of the conflict and the social location of the aggrieved party will condition the social control response. I test propositions drawn from this model with individual-level survey data on a sample of respondents from a metropolitan parish in the south central United States. The results for the empirical test of the theoretical model are mixed. I conclude with suggestions for future research.