Estimation of relative risk for events on a linear network

Motivated by the study of traffic accidents on a road network, we discuss the estimation of the relative risk, the ratio of rates of occurrence of different types of events occurring on a network of lines. Methods developed for two-dimensional spatial point patterns can be adapted to a linear network, but their requirements and performance are very different on a network. Computation is slow and we introduce new techniques to accelerate it. Intensities (occurrence rates) are estimated by kernel smoothing using the heat kernel on the network. The main methodological problem is bandwidth selection. Binary regression methods, such as likelihood cross-validation and least squares cross-validation, perform tolerably well in our simulation experiments, but the Kelsall–Diggle density-ratio cross-validation method does not. We find a theoretical explanation, and propose a modification of the Kelsall–Diggle method which has better performance. The methods are applied to traffic accidents in a regional city, and to protrusions on the dendritic tree of a neuron.

     

Impact of Absolute and Relative Commute Time on Work–Family Conflict: Work Schedule Control,Child Care Hours,and Life Satisfaction

Journal of Family and Economic Issues - Flexibility is crucial when employees manage their work and family demands and their commute between home and work. The current study examined...     

It Takes a Village to Deliver and Test Child and Family-Focused Services

OBJECTIVES: The purpose of this article is to highlight the benefits of collaboration in child focused mental health services research. METHOD: Three unique research projects are described. These projects address the mental health needs of vulnerable, urban, minority children and their families. In each one, service delivery was codesigned, interventions were co-delivered and a team of stakeholders collaboratively tested the impact of each one. RESULTS: The results indicate that the three interventions designed, delivered, and tested are associated with reductions in youth mental health symptoms. CONCLUSION: These interventions are feasible alternatives to traditional individualized outpatient treatment.     

Kernel Density Estimation on a Linear Network

This paper develops a statistically principled approach to kernel density estimation on a network of lines, such as a road network. Existing heuristic techniques are reviewed, and their weaknesses are identified. The correct analogue of the Gaussian kernel is the ‘heat kernel’, the occupation density of Brownian motion on the network. The corresponding kernel estimator satisfies the classical time‐dependent heat equation on the network. This ‘diffusion estimator’ has good statistical properties that follow from the heat equation. It is mathematically similar to an existing heuristic technique, in that both can be expressed as sums over paths in the network. However, the diffusion estimate is an infinite sum, which cannot be evaluated using existing algorithms. Instead, the diffusion estimate can be computed rapidly by numerically solving the time‐dependent heat equation on the network. This also enables bandwidth selection using cross‐validation. The diffusion estimate with automatically selected bandwidth is demonstrated on road accident data.     

A Collaboratively Designed Child Mental Health Service Model: Multiple Family Groups for Urban Children with Conduct Difficulties

This paper presents preliminary outcomes associated with an experimental, longitudinal study of a Multiple Family Group (MFG) service delivery approach set within thirteen urban outpatient clinics serving children and their families living in inner-city, primarily African American and Latino communities. Specifically, this paper focuses on parent reports of child oppositional behavior and parenting stress over time. MFG is a flexible, protocol-driven approach designed to address the most common reason for referral to outpatient child mental health clinics, childhood behavioral difficulties. The MFG also aims to enhance family-level engagement and retention in ongoing care. Further, the service delivery model was collaboratively developed with intensive input from parents rearing children with conduct difficulties, parent advocates, community-based child mental health providers and services research staff in order to ultimately expand the number of effective service models that can be situated within "real world," urban child mental health settings.     

Multiple family groups: an engaging intervention for child welfare-involved families

Differences between child welfare- and non-child welfare-involved families regarding barriers to child mental health care, attendance, program satisfaction, and relationship with facilitators are examined for a multiple family group service delivery model aimed at reducing childhood disruptive behaviors. Although child welfare-involved caregivers reported more treatment barriers and less program satisfaction than non-child-welfare-involved families, no significant differences exist between groups on average total sessions attended and attendance rates over time.     

The intersection of extreme poverty and familial mental health in the United States

Approximately 22% of children in the United States live in poverty, with high rates of caregiver depression and child disruptive behavior disorders (DBD). The current study aims to explore the relationships between living in extreme poverty and both child and parent mental health. Data are comprised of findings from the first effectiveness study of the 4Rs and 2Ss intervention, in addition to preliminary data from an implementation study currently underway (n = 484). Families with an annual income of less than $9,999 reported significantly greater child DBD scores and prevalence of clinically significant levels of caregiver depressive symptoms compared to income levels over $10,000. Findings support the recommendation for parental mental health to be attended to within the context of child mental health services.     

Step-Up: Promoting Youth Mental Health and Development in Inner-City High Schools

African American and Latino youth who reside in inner-city communities are at heightened risk for compromised mental health, as their neighborhoods are too often associated with serious stressors, including elevated rates of poverty, substance abuse, community violence, as well as scarce youth-supportive resources, and mental health care options. Many aspects of disadvantaged urban contexts have the potential to thwart successful youth development. Adolescents with elevated mental health needs may experience impaired judgment, poor problem-solving skills, and conflictual interpersonal relationships, resulting in unsafe sexual behavior and drug use. However, mental health services are frequently avoided by urban adolescents who could gain substantial benefit from care. Thus, the development of culturally sensitive, contextually relevant and effective services for urban, low-income African American and Latino adolescents is critical. Given the complexity of the mental health and social needs of urban youth, novel approaches to service delivery may need to consider individual (i.e., motivation to succeed in the future), family (i.e., adult support within and outside of the family), and community-level (i.e., work and school opportunities) clinical components. Step-Up, a high school-based mental health service delivery model has been developed to bolster key family, youth and school processes related to youth mental health and positive youth development. Step-Up (1) intervenes with urban minority adolescents across inner-city ecological domains; (2) addresses multiple levels (school, family and community) in order to target youth mental health difficulties; and (3) provides opportunities for increasing youth social problem-solving and life skills. Further, Step-Up integrates existing theory-driven, evidence-based interventions. This article describes Step-Up clinical goals, theoretical influences, as well as components and key features, and presents preliminary data on youth engagement for two cohorts of students.     

Generalizing the Announced Price Increase Problem*

This paper generalizes the announced price increase problem to consider a variety of practical concerns arising out of applications ranging from foreign exchange fluctuations to upper limits on the purchase of discounted supermarket items. These include limitations on the amount that can be purchased at the old price and/or on the length of the grace period, within which buyers may take advantage of this lower price. These constraints give rise to 16 possible situations. For each situation purchasing and inventory decision rules are developed. A numerical example is discussed to highlight the main features of the models.