Confidence interval estimation of the difference between paired AUCs based on combined biomarkers

In many diagnostic studies, multiple diagnostic tests are performed on each subject or multiple disease markers are available. Commonly, the information should be combined to improve the diagnostic accuracy. We consider the problem of comparing the discriminatory abilities between two groups of biomarkers. Specifically, this article focuses on confidence interval estimation of the difference between paired AUCs based on optimally combined markers under the assumption of multivariate normality. Simulation studies demonstrate that the proposed generalized variable approach provides confidence intervals with satisfying coverage probabilities at finite sample sizes. The proposed method can also easily provide P-values for hypothesis testing. Application to analysis of a subset of data from a study on coronary heart disease illustrates the utility of the method in practice.     

Estimation in capture–recapture models when covariates are subject to measurement errors and missing data

For capture–recapture models when covariates are subject to measurement errors and missing data, a set of estimating equations is constructed to estimate population size and relevant parameters. These estimating equations can be solved by an algorithm similar to the EM algorithm. The proposed method is also applicable to the situation when covariates with no measurement errors have missing data. Simulation studies are used to assess the performance of the proposed estimator. The estimator is also applied to a capture–recapture experiment on the bird species Prinia flaviventris in Hong Kong. The Canadian Journal of Statistics 37: 645–658; 2009 © 2009 Statistical Society of Canada     

Diagnostic checks for discrete data regression models using posterior predictive simulations

Model checking with discrete data regressions can be difficult because the usual methods such as residual plots have complicated reference distributions that depend on the parameters in the model. Posterior predictive checks have been proposed as a Bayesian way to average the results of goodness-of-fit tests in the presence of uncertainty in estimation of the parameters. We try this approach using a variety of discrepancy variables for generalized linear models fitted to a historical data set on behavioural learning. We then discuss the general applicability of our findings in the context of a recent applied example on which we have worked. We find that the following discrepancy variables work well, in the sense of being easy to interpret and sensitive to important model failures: structured displays of the entire data set, general discrepancy variables based on plots of binned or smoothed residuals versus predictors and specific discrepancy variables created on the basis of the particular concerns arising in an application. Plots of binned residuals are especially easy to use because their predictive distributions under the model are sufficiently simple that model checks can often be made implicitly. The following discrepancy variables did not work well: scatterplots of latent residuals defined from an underlying continuous model and quantile–quantile plots of these residuals.     

Economics, law, and covenant marriage

Covenant marriage may be difficult to understand as a gender issue. However, marriage and divorce are closely linked to workforce participation and child rearing. This piece looks at new proposals for choices in divorce regime from legal, economic, and social perspectives, concluding that the option of contracting a more permanent form of marriage increases the possibilities for women and signals societal interest in promoting more stable families. The article favorably compares Louisiana covenant marriage legislation to other states' suggestions for returns to fault-only regimes, and pays some attention to the role one state's marriage and divorce laws play in the federal system.     

Late fertility decline in the Netherlands: The influence of religious denomination,socioeconomic group and region

Both published results from the 1930, 1947, 1960 and 1971 censuses and unpublished ones are used to examine the influence that religious denomination, socio-economic group and region exerted on the fertility of marriages contracted between 1876 and 1959. A theory formulated by Lesthaeghe and Wilson on the relation between modes of production and secularization and the pace of fertility decline in Western Europe offers — in combination with van Heek's views on the special position of Dutch Roman Catholicism — a starting point for an explanation of why the fertility decline of Roman Catholics, self-employed and agricultural labourers lagged behind.     

在竞争与合作中创建世界城市——以苏格兰中部地区城市为例

本文分析和比较了增长集群不同种类的发展,从集群角度看,重点放在本地的互动和创新方面,并且证明是有益的,因为越来越多的经济活动跨越了传统经济部门和创新的范围.为了能够分析和比较不同集群的不同类别,本文构建了一个提升城市竞争力的分析框架,从空间经济条件、集群的特定条件及集群的组织能力三大要素出发,在城市范围内对集群进行深入分析,同时详细阐述了三大要素在集群发展中的作用.     

Widening the social context of disablement among married older adults: Considering the role of nonmarital relationships for loneliness

Utilizing the stress process and life course perspectives, we investigated the influence of non-spousal social support on the associations between marital quality, physical disability, and loneliness among married older adults. Using data from the National Social Life, Health, and Aging Project (NSHAP), we found that the association between physical disability and loneliness was partially accounted for by the fact that physical disability was associated with less supportive nonmarital relationships. While physically-disabled older adults in higher-quality marriages were buffered from loneliness, supportive non-martial relationships did not offset elevated loneliness among those in low-quality marriages. These associations were largely similar for men and women. Thus, although both marital and nonmarital relationships are important for loneliness, when confronted with a stressor such as disablement it is the marital relationship alone that matters.     

Differentiated leader–member exchange,justice climate,and performance: Main and interactive effects

Leaders form different quality leader–member exchange (LMX) relationships with their subordinates. This variable treatment termed LMX differentiation can have negative effects on individuals' behavior and attitudes. In this study, we examined the cross-level main effect of justice climate on task performance and the moderating role of justice climate on the relationship between LMX differentiation and task performance. We tested these two hypotheses using a field study of 90 subordinates nested under 27 supervisors. Procedural justice climate, not distributive justice climate, was found to positively influence subordinate task performance. Further, distributive justice climate, not procedural justice climate, was found to moderate the LMX differentiation–task performance relationship; such that the relationship was positive when distributive justice climate was high and negative when distributive justice climate was low. Findings and future directions are discussed.