Improved Transferability of Data‐Driven Damage Models Through Sample Selection Bias Correction

Damage models for natural hazards are used for decision making on reducing and transferring risk. The damage estimates from these models depend on many variables and their complex sometimes nonlinear relationships with the damage. In recent years, data‐driven modeling techniques have been used to capture those relationships. The available data to build such models are often limited. Therefore, in practice it is usually necessary to transfer models to a different context. In this article, we show that this implies the samples used to build the model are often not fully representative for the situation where they need to be applied on, which leads to a “sample selection bias.” In this article, we enhance data‐driven damage models by applying methods, not previously applied to damage modeling, to correct for this bias before the machine learning (ML) models are trained. We demonstrate this with case studies on flooding in Europe, and typhoon wind damage in the Philippines. Two sample selection bias correction methods from the ML literature are applied and one of these methods is also adjusted to our problem. These three methods are combined with stochastic generation of synthetic damage data. We demonstrate that for both case studies, the sample selection bias correction techniques reduce model errors, especially for the mean bias error this reduction can be larger than 30%. The novel combination with stochastic data generation seems to enhance these techniques. This shows that sample selection bias correction methods are beneficial for damage model transfer.     

An Evaluation of Mechanisms of Change in Multisystemic Therapy for Juvenile Justice‐Involved Youths A Decade Following Treatment

Although researchers have identified the more immediate mechanisms of change in family‐based treatments for juvenile justice‐involved youths, it is not known whether these same mechanisms continue to prevent criminal offending into adulthood. The present study evaluated whether caregiver‐directed improvements in family relations, youth prosocial peer relations, and youth academic performance during multisystemic therapy (MST) for serious and violent juvenile offenders had an impact on young adult involvement in criminal activity and sentencing 10.2 years following treatment. The results showed that improvements in family relations were associated with reduced odds of criminal outcomes a decade later for former MST participants. Furthermore, improvements in youth prosocial peer relations and academic performance were also related to lower odds of long‐term criminal activity. These results are consistent with the underlying theory of change in family‐based treatments and demonstrate that caregivers are critical to achieving and sustaining decreased antisocial behavior for youths with serious and violent criminal histories.     

Intergenerational cooperation within the household: a Public Good game with three generations

We analyze cooperation of individuals in a family context, using a Public Good game. In a lab experiment, 165 individuals from 55 three-generation families (youth, parent, and grandparent) play a repeated Public Good game in three different treatments: one in which three members of the same family play each other (family), a second with the youth and two non-family members, while preserving the previous generational structure (inter-generational), and a third in which three randomly-selected players play each other (random). We find that all the age groups cooperate more when playing with relatives, indicating that family ties may have a positive relationship to contributions to the Public Good. We also find that this trend is more evident for the youths and the parents than for the grandparents. Furthermore, young individuals tend to cooperate less than older generations, especially in non-family treatments. Our results serve as evidence of the relationship between family ties and inter-generational cooperative behaviors.

     

A reflected feature space for CART

We present an algorithm for learning oblique decision trees, called HHCART(G). Our decision tree combines learning concepts from two classification trees, HHCART and Geometric Decision Tree (GDT). HHCART(G) is a simplified HHCART algorithm that uses linear structure in the training examples, captured by a modified GDT angle bisector, to define splitting directions. At each node, we reflect the training examples with respect to the modified angle bisector to align this linear structure with the coordinate axes. Searching axis parallel splits in this reflected feature space provides an efficient and effective way of finding oblique splits in the original feature space. Our method is much simpler than HHCART because it only considers one reflected feature space for node splitting. HHCART considers multiple reflected feature spaces for node splitting making it more computationally intensive to build. Experimental results show that HHCART(G) is an effective classifier, producing compact trees with similar or better results than several other decision trees, including GDT and HHCART trees.     

Policy Learning and Transformational Change: University Policies on Sexual Harassment

ABSTRACT

This essay comes out of my experience as an attendee at the #MeTooPoliSci short course in the American Political Science Association meeting in 2018. I use the framework of policy feedback theory to explain the difficulty in reforming sexual harassment policies at universities and prescribe some actions we as scholars can take to improve the situations at our places of employment.     

Childhood exposure to polluted neighborhood environments and intergenerational income mobility,teenage birth,and incarceration in the USA

Population and Environment - This paper joins a growing body of research linking measures of the physical environment to population well-being, with a focus on neighborhood toxins. Extending a...     

Wanting To Be Remembered: Intrinsically Rewarding Work and Generativity in Early Midlife

Previous research on generativity, the desire to leave a legacy through establishing and guiding the next generation, has focused primarily on family life and civic engagement as pathways to midlife generativity. This paper proposes that intrinsically rewarding work can also be associated with a heightened sense of generativity in midlife. We test this hypothesis with data (n = 369 employed individuals, approximately 43 years old) from the 2010 wave of the Edmonton Transitions Study. Civic engagement was positively associated with midlife generativity, as predicted, but the hypothesized positive relationship between generativity and perceived parenting success was not found. Taking into account civic engagement and perceived parenting success, and controlling on a range of other variables, intrinsically rewarding work was positively associated with midlife feelings of generativity.     

Accurate computation of single and product moments of order statistics under progressive censoring

An accurate procedure is proposed to calculate approximate moments of progressive order statistics in the context of statistical inference for lifetime models. The study analyses the performance of power series expansion to approximate the moments for location and scale distributions with high precision and smaller deviations with respect to the exact values. A comparative analysis between exact and approximate methods is shown using some tables and figures. The different approximations are applied in two situations. First, we consider the problem of computing the large sample variance–covariance matrix of maximum likelihood estimators. We also use the approximations to obtain progressively censored sampling plans for log-normal distributed data. These problems illustrate that the presented procedure is highly useful to compute the moments with precision for numerous censoring patterns and, in many cases, is the only valid method because the exact calculation may not be applicable.     

Three Recommendations for Improving the Use of p-Values

ABSTRACT

Researchers commonly use p-values to answer the question: How strongly does the evidence favor the alternative hypothesis relative to the null hypothesis? p-Values themselves do not directly answer this question and are often misinterpreted in ways that lead to overstating the evidence against the null hypothesis. Even in the “post p?<?0.05 era,” however, it is quite possible that p-values will continue to be widely reported and used to assess the strength of evidence (if for no other reason than the widespread availability and use of statistical software that routinely produces p-values and thereby implicitly advocates for their use). If so, the potential for misinterpretation will persist. In this article, we recommend three practices that would help researchers more accurately interpret p-values. Each of the three recommended practices involves interpreting p-values in light of their corresponding “Bayes factor bound,” which is the largest odds in favor of the alternative hypothesis relative to the null hypothesis that is consistent with the observed data. The Bayes factor bound generally indicates that a given p-value provides weaker evidence against the null hypothesis than typically assumed. We therefore believe that our recommendations can guard against some of the most harmful p-value misinterpretations. In research communities that are deeply attached to reliance on “p?<?0.05,” our recommendations will serve as initial steps away from this attachment. We emphasize that our recommendations are intended merely as initial, temporary steps and that many further steps will need to be taken to reach the ultimate destination: a holistic interpretation of statistical evidence that fully conforms to the principles laid out in the ASA statement on statistical significance and p-values.