Semi-parametric estimation of ROC curves based on binomial regression modelling

This paper presents a method of estimating a receiver operating characteristic (ROC) curve when the underlying diagnostic variable X is continuous and fully observed. The new method is based on modelling the probability of response given X , rather than the distribution of X given response. The method offers advantages in modelling flexibility and computational simplicity. The resulting ROC curve estimates are semi-parametric and can, in principle, take an infinite variety of shapes. Moreover, model selection can be based on standard methods within the binomial regression framework. Statistical accuracy of the curve estimate is provided by a simply implemented bootstrap approach.     

Measuring Children's Experience of Their Right to Participate in School and Community: A Rights‐Based Approach

This paper discusses the development of a children's rights‐based measure of participation and the findings from its use in a survey of 10‐ to 11‐year‐old children (n = 3773). The measure, which was developed in collaboration with a group of children, had a high reliability (Cronbach's alpha = 0.89). Findings suggest that children's positive experience of their participation rights is higher in school than in community, and higher for girls compared to boys. It is argued that involving children in the ‘measurement’ of their own lives has the potential to generate more authentic data on children's lived experiences.     

A green space vision in Southeast Michigan’s most heavily industrialized area

Urban Ecosystems - In 2011, Marathon Petroleum Company LP, which has operated a refinery west of the Rouge River since 1959, initiated a voluntary property purchase program in the neighborhood...     

Multidimensional Resilience: Predictive and Construct Validity of the Individual,Family, and Community Resilience Profile

Few measures parallel the robust depth offered in the existing multidimensional and ecologically informed theories of resilience. This study sought to evaluate the test–retest reliability, construct, and predictive validity of the individual, family, and community resilience resource profile (IFCR-R). The IFCR-R measures a family’s access to resilience resources and protective factors across multiple ecological levels. Confirmatory factor analysis was used with a sample of n?=?810 low-income families. And 159 families completed multiple time point measures for test–retest reliability and predictive validity evaluation. Results of this study support the proposed multidimensional ecological structure of the IFCR-R and found that the IFCR-R offers an acceptable test–retest reliability and predictive validity for outcomes of mental and physical health.     

Increasing Competency,Self-Confidence,and Connectedness Among Foster Care Alumni Entering a 4-Year University: Findings from an Early-Start Program

Research shows that few foster care alumni enroll and complete post-secondary education. For those who do enroll, many experience challenges associated with academic and social adjustment and are at risk of dropping out. Many college-based programs are being developed and are available to foster care alumni to support them during their post-secondary education. This study used pre-tests, post-tests, and journal entries of seventeen participants to evaluate a strengths-based, resilience-oriented early-start program for newly enrolled students at a large public university that provides knowledge about the institution, resources (e.g., tutoring), and social support necessary for foster care alumni to make a smooth transition into college life and to increase short and long-term student success. Quantitative and qualitative findings indicate that students who participated in the early-start program showed increased confidence and competency in academic and social adjustment. Findings also showed personal growth (e.g., building resiliency) and an increased connectedness among students who participated in the program. Study findings can inform the development of new on-campus support programs and help enhance existing programming. Future research should address short and long-term outcomes and experiences of students who are former foster youth who have participated in on-campus support programs.     

Shared services centers and work sustainability: which contributions from ergonomics?

This study examines the way in which Shared Services Centers (SSCs) were implemented in a French multinational company. It aims to characterize the change according to the capabilities model developed by Amartya Sen: what are the effects of SSCs in terms of capabilities development and developmental quality of work, i.e. in the enabling potential of work? A 3-step methodology has been used: first, an investigation was conducted in a pay service of a local entity moving into SSC in 2013; second, two investigations were conducted in another pay service of a SSC: first, a few months after the change, and then, one year after the change (the same operators were interviewed). Results show a tendency to the decrease of the enabling potential. Additionally, it was noted that administrators are kept away from the design process and have to struggle with inappropriate rules. The efficiency and sustainability of the SSC are questioned; in this context, the human factor specialist has an important role to play.     

Impact of the National Minimum Wage on Disabled People

The survey reported here found disparities in the impact of the introduction of the National Minimum Wage on disabled people. These were associated with age, gender, impairment and type of employment setting. The main determinant of whether individuals gained from the NMW was their status as claimants of welfare benefits. We also found evidence that paid hours had been reduced to implement the NMW with no net increase in earnings, possibly to enable people to retain benefits entitlements. We make recommendations about how the anomalies can be tackled. It may be unrealistic to expect the Act to have been implemented fully so soon after it became law and some of the anomalies found may eventually disappear. However, many of the inequalities uncovered by this survey are not addressed by the NMW, specifically those inequalities associated with impairment and gender.     

Estimating a frequency distribution when the sampling is biased

A simple random sample on a random variable A allows its density to be consistently estimated, by a histogram or preferably a kernel density estimate. When the sampling is biased towards certain x-values these methods instead estimate a weighted version of the density function. This article proposes a method for estimating both the density and the sampling bias simultaneously. The technique requires two independent samples and utilises ideas from mark-recapture experiments. An estimator of the size of the sampled population also follows simply from this density estimate.