Exact Bayesian inference for off-line change-point detection in tree-structured graphical models

We consider the problem of change-point detection in multivariate time-series. The multivariate distribution of the observations is supposed to follow a graphical model, whose graph and parameters are affected by abrupt changes throughout time. We demonstrate that it is possible to perform exact Bayesian inference whenever one considers a simple class of undirected graphs called spanning trees as possible structures. We are then able to integrate on the graph and segmentation spaces at the same time by combining classical dynamic programming with algebraic results pertaining to spanning trees. In particular, we show that quantities such as posterior distributions for change-points or posterior edge probabilities over time can efficiently be obtained. We illustrate our results on both synthetic and experimental data arising from biology and neuroscience.     

Validating Grant-Making Processes: Construct Validity of the 2013 Senior Corps RSVP Grant Review

Accountability in grant-making requires a valid, fair and transparent selection process. This study proposes a four-step framework for validating such a process: determine standards for qualified applicants, assess inter-reviewer reliability, assess factorial validity, and assess reliability. This framework is applied to the Corporation for National and Community Service’s 2013 RSVP grant-making process. The standards were close to the highest points of reliability. Inter-reviewer reliability was above 0.90, a common threshold for high-stakes measurement. After conducting confirmatory factor analysis, the final model merged two of the original five domains of selection criteria, resulting in four domains. The final model was found to have strict measurement invariance, high convergent validity, and measurement reliability between 0.88 and 0.93 for all domains. The results validate the 2013 review process and indicated that the scores exhibited high degrees of reliability, giving public assurance that the process was sufficiently objective and accurately reflected program priorities.     

Improving the Impact and Implementation of Disaster Education: Programs for Children Through Theory‐Based Evaluation

A main weakness in the evaluation of disaster education programs for children is evaluators’ propensity to judge program effectiveness based on changes in children's knowledge. Few studies have articulated an explicit program theory of how children's education would achieve desired outcomes and impacts related to disaster risk reduction in households and communities. This article describes the advantages of constructing program theory models for the purpose of evaluating disaster education programs for children. Following a review of some potential frameworks for program theory development, including the logic model, the program theory matrix, and the stage step model, the article provides working examples of these frameworks. The first example is the development of a program theory matrix used in an evaluation of ShakeOut, an earthquake drill practiced in two Washington State school districts. The model illustrates a theory of action; specifically, the effectiveness of school earthquake drills in preventing injuries and deaths during disasters. The second example is the development of a stage step model used for a process evaluation of What's the Plan Stan?, a voluntary teaching resource distributed to all New Zealand primary schools for curricular integration of disaster education. The model illustrates a theory of use; specifically, expanding the reach of disaster education for children through increased promotion of the resource. The process of developing the program theory models for the purpose of evaluation planning is discussed, as well as the advantages and shortcomings of the theory‐based approaches.     

At Home on the Range? Lay Interpretations of Numerical Uncertainty Ranges

Numerical uncertainty ranges are often used to convey the precision of a forecast. In three studies, we examined how users perceive the distribution underlying numerical ranges and test specific hypotheses about the display characteristics that affect these perceptions. We discuss five primary conclusions from these studies: (1) substantial variation exists in how people perceive the distribution underlying numerical ranges; (2) distributional perceptions appear similar whether the uncertain variable is a probability or an outcome; (3) the variation in distributional perceptions is due in part to individual differences in numeracy, with more numerate individuals more likely to perceive the distribution as roughly normal; (4) the variation is also due in part to the presence versus absence of common cues used to convey the correct interpretation (e.g., including a best estimate increases perceptions that the distribution is roughly normal); and (5) simple graphical representations can decrease the variance in distributional perceptions. These results point toward significant opportunities to improve uncertainty communication in climate change and other domains.     

Trajectories of English Acquisition among Foreign‐born Spanish‐Language Children in the United States

The rapidity with which immigrant children learn the dominant language of their country of residence has important short‐term and long‐term consequences for their educational achievements and for their future. In this paper I use US Census data to model trajectories of English acquisition among foreign‐born children living in Spanish‐language households. The results show, as expected, that children's English proficiency increases with length of residence in the United States. However, the results also show a clear trend by age at arrival. The older children are when they arrive in the United States, the less rapid their progress in acquiring proficiency in English.     

Does Financial Satisfaction Vary Depending on the Funding Strategy Used to Pay for College?

This study sought to determine whether the levels of financial satisfaction reported by college undergraduates and graduates differ in relation to whether they funded their college education by working or borrowing or a combination of the two. Data for this study came from a survey sample of full-time freshmen that formed the basis of a longitudinal study conducted at a large public university. Funding sources examined were grouped into those who worked only, those who borrowed only, those who worked and borrowed, and those who used grants, scholarships, or other sources of money to fund their college education. Compared to those who had student loans, those who had financed college with grants, scholarships, or other money (usually from family and/or friends) were more likely to report greater financial satisfaction than those who had used student loans to pay for college. There was evidence that this was only true during college rather than after college. The results obtained suggest that merely possessing a student loan may not necessarily decrease the level of financial satisfaction as many suspect, especially considering other funding alternatives such as working during college. While there was no significant impact of these funding strategies on financial satisfaction either during or after college, there was evidence for possible thresholds at which overall student loan balances may begin to erode financial satisfaction. The results obtained suggest that student loans may not decrease the level of financial satisfaction as much as many have suspected when compared with working to pay for college, as long as the amount of the student loan is not excessive, and is not accompanied by other types of debt (which also reduced financial satisfaction).

     

Implicit Leadership and Followership Theories “in the wild”: Taking stock of information-processing approaches to leadership and followership in organizational settings

For over 30 years information-processing approaches to leadership and more specifically Implicit Leadership Theories (ILTs) research has contributed a significant body of knowledge on leadership processes in applied settings. A new line of research on Implicit Followership Theories (IFTs) has re-ignited interest in information-processing and socio-cognitive approaches to leadership and followership. In this review, we focus on organizational research on ILTs and IFTs and highlight their practical utility for the exercise of leadership and followership in applied settings. We clarify common misperceptions regarding the implicit nature of ILTs and IFTs, review both direct and indirect measures, synthesize current and ongoing research on ILTs and IFTs in organizational settings, address issues related to different levels of analysis in the context of leadership and follower schemas and, finally, propose future avenues for organizational research.     

A Benefit-Cost Analysis of Retrofitting Diesel Vehicles with Particulate Filters in the Mexico City Metropolitan Area

In the Mexico City metropolitan area, poor air quality is a public health concern. Diesel vehicles contribute significantly to the emissions that are most harmful to health. Harmful diesel emissions can be reduced by retrofitting vehicles with one of several technologies, including diesel particulate filters. We quantified the social costs and benefits, including health benefits, of retrofitting diesel vehicles in Mexico City with catalyzed diesel particulate filters, actively regenerating diesel particulate filters, or diesel oxidation catalysts, either immediately or in 2010, when capital costs are expected to be lower. Retrofit with either type of diesel particulate filter or an oxidation catalyst is expected to provide net benefits to society beginning immediately and in 2010. At current prices, retrofit with an oxidation catalyst provides greatest net benefits. However, as capital costs decrease, retrofit with diesel particulate filters is expected to provide greater net benefits. In both scenarios, retrofit of older, dirtier vehicles that circulate only within the city provides greatest benefits, and retrofit with oxidation catalysts provides greater health benefits per dollar spent than retrofit with particulate filters. Uncertainty about the magnitude of net benefits of a retrofit program is significant. Results are most sensitive to values used to calculate benefits, such as the concentration-response coefficient, intake fraction (a measure of exposure), and the monetary value of health benefits.     

Constructing Interracial Families Through Intercountry Adoption*

Objective. This article analyzes the role of race and ethnicity in constructing American families through intercountry adoption. We argue that such adoptions illustrate the fluidity and tenacity of specific racial boundaries in American families. Methods. Data are drawn from the U.S. 2000 Census—the first to contain information on children's adoptive status—to examine whether race of parents and adopted children match and whether racial matching varies by the characteristics of adoptive families and adopted children. Results. Our findings indicate that minority‐race parents are more likely than white parents to adopt a child of the same race as themselves, and that the odds of white parents, in particular, adopting a white versus nonwhite child from abroad are related to factors such as the age, sex, and health status of the child, as well the presence of other children in the household. Conclusion. Parents weigh a constellation of factors, including attributes of the adopted child and the children already in the household, when adopting a child of the same or different race from abroad.