Choosing Between the Sample-Selection Model and the Multi-Part Model

Hay and Olsen (1984) incorrectly argue that a multi-part model, the two-part model used in Duan et al. (1982,1983), is nested within the sample-selection model. Their proof relies on an unmentioned restrictive assumption that cannot be satisfied. We provide a counterexample to show that the propensity to use medical care and the level of expense can be positively associated in the two-part model, contrary to their assertion. The conditional specification in the multi-part model is preferable to the unconditional specification in the selection model for modeling actual (v. potential) outcomes. The selection model also has poor statistical and numerical properties and relies on untestable assumptions. Empirically the multi-part estimators perform as well as or better than the sample selection estimator for the data set analyzed in Duan et al. (1982, 1983).     

ARE WINNERS PROMOTED TOO OFTEN? EVIDENCE FROM THE NFL DRAFT 1999–2012

Firms engaging in hiring face recruitment costs. To reduce these costs, firms concentrate their efforts in locations that are perceived as talent rich or have produced successful employees in the past. Such recruitment mechanisms may lead to statistical discrimination if they reduce uncertainty for a subset of candidates or if firms relate current employee attributes with the institution. In this article, I test for statistical discrimination associated with an individual's institutional affiliation that results from targeted hiring practices by using a unique individual‐level data set of National Football League (NFL) draft prospects. I find that conditional on individual ability, individuals from highly ranked college teams are drafted earlier than individuals from lower ranked institutions. Over the length of a player's professional career, a player's college institution has no effect on career success, indicating that certain players are damaged by this recruitment mechanism. Even though players can suffer substantial financial damages as a result of being drafted later in the draft, NFL team performance is not sufficiently affected for teams to exploit this bias. (JEL J71, J31)     

A structured procedure for materials planning during production transfer

This paper explores materials planning procedures to ensure the materials’ availability during production transfers. The paper defines a production transfer as the preparation, physical transfer and start-up of relocated production. A structured procedure of materials planning during production transfer is developed based on theory, and then validated and refined based on the analysis of four case studies. The paper shows that there is a need for a structured procedure of materials planning during production transfers. It also explains the importance of activities that create prerequisites for the materials’ availability during production transfer, such as updating and adapting documentation, planning and control systems, and describes the activities that ensure the materials’ availability, such as preventive and corrective actions. A valid estimation of the time needed to reach a steady state and a combination of several preventive actions improves the ability to ensure that materials are available. The cases showed differences across company size, because large companies took more and farther-reaching preventive actions.     

Social capital and political fantasy: Robert Putnam’sbowling alone

Theory and Society -     

Bayesian analysis of mark‐recapture data with travel time‐dependent survival probabilities

The authors extend the classical Cormack‐Jolly‐Seber mark‐recapture model to account for both temporal and spatial movement through a series of markers (e.g., dams). Survival rates are modeled as a function of (possibly) unobserved travel times. Because of the complex nature of the likelihood, they use a Bayesian approach based on the complete data likelihood, and integrate the posterior through Markov chain Monte Carlo methods. They test the model through simulations and apply it also to actual salmon data arising from the Columbia river system. The methodology was developed for use by the Pacific Ocean Shelf Tracking (POST) project.     

Fertility and development: evidence from Brazil

Using microdata from the Brazilian demographic censuses of 1960, 1970, 1980, and 1991, aggregated into 518 consistently defined spatial units called microregions, we estimated fertility and mortality and constructed indicators of development and living conditions in the rural and urban areas of the microregions in each census. We then estimated cross-sectional and fixed-effects models to answer questions about the degree to which changes in these indicators are associated with changes in fertility and whether the relationship between fertility and development shifts through time. We found strong and consistent relationships between the decline in fertility and measurable changes in social and economic circumstances.     

School Choice, Markets and Special Educational Needs

Locating the debate within a policy framework of school choice and special educational needs (SEN) in England and Wales, the article investigates the ways in which schools competing within the educational marketplace perceive and respond to the needs of parents of SEN students, and considers the perspectives, experiences and values of these parents relating to school choice. In focusing in-depth on one case study area the article draws on the qualitative findings of the Parental and School Choice Interaction (PASCI) study, a 3-year longitudinal investigation into the interaction between parental choice of school and school decision making. The findings reveal the pressures on senior school managers and the difficulties encountered by parents of SEN students and suggest that as schools working in a public-market increasingly 'privilege the academic' so the needs and preferences of parents, and SEN students are increasingly marginalised and devalued.     

MORTALITY,HEALTH STATUS,AND WEALTH

In this paper we use the two waves of the British Retirement Survey (1988/1989 and 1994) to quantify the relationship between socioeconomic status and health outcomes. We find that, even after conditioning on the initial health status, wealth rankings are important determinants of mortality and the evolution of the health indicator in the survey. For men aged 65 moving from the 40th percentile to the 60th percentile in the wealth distribution increases the probability of survival by between 1.0 and 1.9 percentage points depending on the measure of wealth used. A similar effect is found for women of between 1.1 and 1.3 percentage points. In the process of estimating these effects we control for nonrandom attrition from our sample. (JEL: I2, J19)     

How does discharge status impact suicide risk in military veterans?

Little is known about over 125,000 veterans who received non-honorable military discharges since 2001, even though these veterans face substantial barriers to obtaining services and are likely to be at high risk for negative mental and behavioral health outcomes including suicide. Seven-hundred twenty-two veterans living the in the San Francisco Bay Area participated in the study. The sample comprised honorably discharged (n = 508) and non-honorably discharged veterans (n = 214). T-tests were used to compare means on predictors of suicide risk including Posttraumatic Stress Disorder (PTSD), depression, alcohol use, somatic symptoms, and physical disability. A series of regression models tested relationships between predictors, discharge status, and suicide risk. Non-honorably discharged veterans demonstrated higher mean scores than honorably discharged veterans on all predictors. In regression models, somatic symptoms (β = 0.22, p < 0.001), physical disability (β = 0.16, p < 0.05), and discharge status (β = 0.33, p < 0.001) were associated with suicide risk. The final model showed an interaction effect for discharge status on the relationship between somatic symptoms and suicide risk (β = 0.16, p < 0.05). Non-honorably discharged veterans showed higher rates of mental and physical health problems and suicide risk compared to honorably discharged veterans. The magnitude of the relationship between somatic symptoms and suicide risk was significantly greater in non-honorably discharged veterans.