Model checks for Cox-type regression models based on optimally weighted martingale residuals

We introduce directed goodness-of-fit tests for Cox-type regression models in survival analysis. “Directed” means that one may choose against which alternatives the tests are particularly powerful. The tests are based on sums of weighted martingale residuals and their asymptotic distributions. We derive optimal tests against certain competing models which include Cox-type regression models with different covariates and/or a different link function. We report results from several simulation studies and apply our test to a real dataset.     

在孔子与罗素之间——访罗素专家张申府

本文摘自美国历史学家Ｖｅｒａ Ｓｃｈｗａｒｃｚ的访谈集《真言》。该书涉及了哲学家张申府的政治和学术活动,是一本以西方学者眼光反映中国知识分子的有价值的书籍。     

The Role of Co-worker and Supervisor Support in the Relationship Between Job Autonomy and Work Engagement Among Portuguese Nurses: A Multilevel Study

The objective is to analyze the relationship between job resources (i.e., job autonomy and social support) and work engagement in nurses. Hypotheses have been tested through hierarchical linear modeling using data from 313 Portuguese nurses (individual level) nested in 33 work teams (team level), after aggregating individual perceptions to the group level and testing the agreement among these perceptions using the r_wg(j) and the intraclass correlations indices. Results confirmed first, that individual job autonomy and team-level social support (from the supervisor as well as from co-workers) are positively related to individual work engagement and second, that team-level social support has a moderating effect on the relationship between individual job autonomy and individual work engagement (but not in the case of co-workers’ support). This study provides evidence that nurses’ work engagement results from individual job autonomy and collective social support. Accordingly, fostering job autonomy and social support in order to promote work engagement among nurses can be useful for both hospital managers and practitioners.     

Food Assistance Programs and Outcomes in the Context of Welfare Reform*

Objective. Food assistance programs play an important role in meeting the basic needs of low‐income households. We consider how the Food Stamp Program (FSP), labor force participation, and food insecurity status affect outcomes of low‐income households under different program designs and economic conditions. Methods. Data from the Survey of Program Dynamics allow estimation of the effects of participation in FSP, labor market participation, and food insecurity on each other. To obtain estimates of behavioral relationships, we apply a simultaneous equation model and make a set of plausible assumptions about identification to implement the instrumental variable estimation. Results. Food insecurity has a positive effect on FSP participation, while labor force participation reduces FSP participation. Furthermore, FSP participation is more responsive to changes in the amount of program benefits than to changes in nonlabor income. Labor force participation has no direct effect on food insecurity; although not statistically significant, the effect of FSP participation on food insecurity is positive. A higher wage rate decreases FSP participation and increases participation in the labor force. Conclusion. The structural approach, which relies on particular identifying assumptions, allows us to explicity examine linkages among food program participation, labor force participation, and well‐being, measured in terms of food insecurity. The results provide evidence that among low‐income households, program parameters affect FSP participation, but no evidence that the food assistance reduces food insecurity.     

Importance of Land,family and culture for a good life: Remote Aboriginal people with disability and carers

Worldwide health and social outcomes of Indigenous people are poorer than those of non-Indigenous. In Australia, the Indigenous population experience disability at more than twice the rate of the non-Indigenous population, and a quarter live in geographically remote areas. The challenges associated with accessing services and supports in remote communities can impact on a good life for Aboriginal people with disability. Interviews were conducted with Aboriginal people (An angu) with disability and family carers from remote Central Australian communities and service workers. Thematic data analysis determined factors An angu viewed as essential to living a good life: connection to their Lands, being with family and engaging in cultural activities. Workers' support for a good life involves “Proper Way” help and an understanding of An angu culture. Three culturally relevant strengths-based concepts are important in supporting An angu with disability to live a good life: being connected to the Lands and family, sharing together and working together.     

Race,Ethnicity, and Underemployment in Nonmetropolitan America: A 30‐Year Profile*

Abstract Historically, rural racial and ethnic minorities have been among the most economically disadvantaged groups in the United States. Key to understanding economic deprivation is employment hardship, trends in which serve as a benchmark for progress toward racial and ethnic equality. We conceptualize employment hardship as underemployment, which goes beyond unemployment to include discouraged workers, involuntary part‐time workers, and the working poor. Analyzing data from the March Current Population Surveys of 1968 through 1998, we find that (1) there are large and persistent racial and ethnic inequalities in underemployment prevalence; (2) these disadvantages are explained only partially by other predictors of underemployment; (3) nonmetropolitan (nonmetro) minorities are more likely than either all metropolitan (metro) or central‐city minorities to be underemployed; (4) black‐white inequality has held steady overall, though it has declined markedly in nonmetro areas; and (5) Hispanic‐white inequality has increased; this trend, however, is restricted to metro areas, central cities in particular.     

A BIVARIATE BINOMIAL DISTRIBUTION AND SOME APPLICATIONS1

This study is concerned with the joint distribution of the total numbers of occurrences of binary characters A and B, given three independent samples in which both characters, A but not B, and B but not A, are observed. The distribution function is given; its conditional distributions and regression functions are found; bounds on certain joint probabilities are established; and conditions for bivariate Poisson and Gaussian limits are studied. An application yields the joint distribution of sign statistics for the pair-wise comparison of treatments with a control.     

Social Capital and Human Mortality: Explaining the Rural Paradox with County‐Level Mortality Data

The “rural paradox” refers to standardized mortality rates in rural areas that are unexpectedly low in view of well‐known economic and infrastructural disadvantages there. We explore this paradox by incorporating social capital, a promising explanatory factor that has seldom been incorporated into residential mortality research. We do so while being attentive to spatial dependence, a statistical problem often ignored in mortality research. Analyzing data for counties in the contiguous United States, we find that: (1) the rural paradox is confirmed with both metro‐nonmetro and rural‐urban continuum codes, (2) social capital significantly reduces the impacts of residence on mortality after controlling for race and ethnicity and socioeconomic covariates, (3) this attenuation is greater when a spatial perspective is imposed on the analysis, (4) social capital is negatively associated with mortality at the county level, and (5) spatial dependence is strongly in evidence. A spatial approach is necessary in county‐level analyses such as ours to yield unbiased estimates and optimal model fit.