Zero variance Markov chain Monte Carlo for Bayesian estimators

Interest is in evaluating, by Markov chain Monte Carlo (MCMC) simulation, the expected value of a function with respect to a, possibly unnormalized, probability distribution. A general purpose variance reduction technique for the MCMC estimator, based on the zero-variance principle introduced in the physics literature, is proposed. Conditions for asymptotic unbiasedness of the zero-variance estimator are derived. A central limit theorem is also proved under regularity conditions. The potential of the idea is illustrated with real applications to probit, logit and GARCH Bayesian models. For all these models, a central limit theorem and unbiasedness for the zero-variance estimator are proved (see the supplementary material available on-line).     

Marriage and Subjective Well-Being: How and Why Context Matters

Over the last 20 years the academic community has experienced a burgeoning interest in the causes and correlates of subjective well-being. One of the most consistent findings has been that married respondents report higher levels of happiness and life satisfaction than unmarried respondents. Despite its prevalence, scant empirical research has focused on the potential mechanisms driving this relationship. The current work draws on the Behavior Risk Factor Surveillance System along with 2000 US Census data to investigate the role of context and reference groups in shaping the relationship between marriage and well-being. The primary research question is whether marriage has a greater influence on life satisfaction when it is more common and thus more normative? The findings offer new insight into the marriage/well-being relationship and have broad implication for how we think about the study of the causes and correlates of subjective well-being.     

Caregiver Decision-Making: Household Response to Child Illness in Sub-Saharan Africa

We draw upon a framework outlining household recognition and response to child illness proposed by Colvin et al. (Soc Sci Med 86:66–78, 2013) to examine factors predictive of treatment sought for a recent child illness. In particular, we model whether no treatment, middle layer treatment (traditional healer, pharmacy, community health worker, etc.), or biomedical treatment was sought for recent episodes of diarrhea, fever, or cough. Based on multinomial, multi-level analyses of Demographic and Health Surveys from 19 countries in sub-Saharan Africa, we determine that if women have no say in their own healthcare, they are unlikely to seek treatment in response to child illness. We find that women in sub-Saharan Africa need healthcare knowledge, the ability to make healthcare decisions, as well as resources to negotiate cost and travel, in order to access biomedical treatment. Past experience with medical services such as prenatal care and a skilled birth attendant also increases the odds that biomedical treatment for child illness is sought. We conclude that caregiver decision-making in response to child illness within households is critical to reducing child morbidity and mortality in sub-Saharan Africa.     

Evaluation of Alternative Cohort-Component Models for Local Area Population Forecasts

It is generally accepted by demographers that cohort-component projection models which incorporate directional migration are conceptually preferable to those using net migration. Yet net migration cohort-component models, and other simplified variations, remain in common use by both academics and practitioners because of their simplicity and low data requirements. While many arguments have been presented in favour of using one or other type of model, surprisingly little analysis has been undertaken to assess which tend to give the most accurate forecasts. This paper evaluates five cohort-component models which differ in the way they handle migration, four of which are well known, with one—a composite net migration model—being proposed here for the first time. The paper evaluates the performance of these five models in their unconstrained form, and then in a constrained form in which age–sex-specific forecasts are constrained to independent total populations from an extrapolative model shown to produce accurate forecasts in earlier research. Retrospective forecasts for 67 local government areas of New South Wales were produced for the period 1991–2011 and then compared to population estimates. Assessments of both total and age-specific population forecasts were made. The results demonstrate the superior performance of the forecasts constrained to total populations from the extrapolative model, with the constrained bi-regional model giving the lowest errors. The findings should be of use to practitioners in selecting appropriate models for local area population forecasts.     

Type of Health Facility and Utilization of Antenatal Care Services Among Ghanaian Women

This study examined if differences exist in the number and timing of antenatal care (ANC) visits for users of public and private health care facilities in Ghana. Also, the study explored if such variations could be attributed to health-provider factors or the selective socioeconomic characteristics of the users. Data were drawn from the recently collected Ghana Demographic and Health Survey and from a representative sample of t 2135 women who attended antenatal care in a health facility 6 months preceding the survey. Random-effects Poisson and logit models were employed for analysis. Results showed statistically significant differences between users of private and public health facilities for number of ANC visits, but not for the timing of such visits. Although some health-provider factors were significantly associated with ANC visits, these factors did not explain why users of private health facilities had significantly higher number of ANC visits than users of public health facilities. Differences in ANC visits for both private and public health facilities were rather explained by the selective socioeconomic characteristics of the users, especially as wealthy and educated women patronized private health care than poorer and uneducated women. The study concludes that Ghanaian women attending private health facilities may not have improved access to antenatal care compared to those attending public health facilities, and adds to the emerging body of literature that questions private health care in sub-Saharan Africa as more effective than public health care.     

Changes in Cohabitation After the Birth of the First Child in Chile

In Chile, as in other Latin American countries, most children born outside of marriage are born to currently cohabiting couples. After having their first child, parents could marry, separate, or experience no change in union status. This paper explores changes in cohabitation that occur after the birth of the first child in Chile and analyzes how these changes might be associated with the birth of children and socioeconomic status. The data come from the New Chilean Family Survey, a small longitudinal survey administered to women after giving birth (n = 564). I use life tables and event history techniques to assess changes in respondent union status up to 4 years after the birth of the first child, and to study the transitions out of cohabitation. The results indicate that the unions in the sample are relatively stable, because less than 40 percent of cohabiters change status over the period of 4 years. However, marriage still appears to be a more stable type of union than cohabitation. Among cohabiters, there is evidence of a nonlinear relation between union stability and educational attainment, because the most stable unions are the unions of women with a high school diploma and not the unions of women who did not complete their secondary education. Having planned the first birth and the birth of an additional child seems to consolidate the cohabiting union, because these variables are not related to the entry into marriage, but they are related to lower risks of dissolution. These findings suggest that the Chilean case differs from the cases of Europe and the United States.     

Computing unique maximum matchings in $$$$ time for König–Egerváry graphs and unicyclic graphs

Let \(\alpha \left( G\right) \) denote the maximum size of an independent set of vertices and \(\mu \left( G\right) \) be the cardinality of a maximum matching in a graph \(G\). A matching saturating all the vertices is a perfect matching. If \(\alpha \left( G\right) +\mu \left( G\right) =\left| V(G)\right| \), then \(G\) is called a König–Egerváry graph. A graph is unicyclic if it is connected and has a unique cycle. It is known that a maximum matching can be found in \(O(m\cdot \sqrt{n})\) time for a graph with \(n\) vertices and \(m\) edges. Bartha (Proceedings of the 8th joint conference on mathematics and computer science, Komárno, Slovakia, 2010) conjectured that a unique perfect matching, if it exists, can be found in \(O(m)\) time. In this paper we validate this conjecture for König–Egerváry graphs and unicylic graphs. We propose a variation of Karp–Sipser leaf-removal algorithm (Karp and Sipser in Proceedings of the 22nd annual IEEE symposium on foundations of computer science, 364–375, 1981) , which ends with an empty graph if and only if the original graph is a König–Egerváry graph with a unique perfect matching (obtained as an output as well). We also show that a unicyclic non-bipartite graph \(G\) may have at most one perfect matching, and this is the case where \(G\) is a König–Egerváry graph.     

A Manager is a Manager is a Manager? Race and Managerial Impact on Organizational Performance

Contemporary scientific analyses of public organizations underscore the salience of management for understanding how governmental bureaucracies perform. Yet little is known of administrators from minority social groups, and whether their organizations perform better or worse than other bureaucracies. Emphasizing the impact of network engagement on organizational performance, this exploratory study addresses this important research deficiency. A critical component of the analysis presented is the differential impact of administrative engagement with internal and external networks on minority and status quo clientele outcomes. The findings have important implications for studies of managerial networking, equity, and representation in public organizations.     

Did Australia’s Baby Bonus Increase Fertility Intentions and Births?

In May 2004, the Australian government announced a “Baby Bonus” policy, paying women an initial A$3,000 per new child. We use household panel data from the Household, Income and Labour Dynamics in Australia Survey (N = 14,932) and a simultaneous equations approach to analyze the effects of this bonus on fertility intentions and ultimately births. The results indicate that opportunity costs influence intentions and births in predictable ways. Fertility intentions rose after the announcement of the Baby Bonus, and the birth rate is estimated to have risen modestly as a result. The marginal cost to the government for an additional birth is estimated to be at least A$3,000 per new child. We use household panel data from the Household, Income and Labour Dynamics in Australia Survey (N = 14,932) and a simultaneous equations approach to analyze the effects of this bonus on fertility intentions and ultimately births. The results indicate that opportunity costs influence intentions and births in predictable ways. Fertility intentions rose after the announcement of the Baby Bonus, and the birth rate is estimated to have risen modestly as a result. The marginal cost to the government for an additional birth is estimated to be at least A126,000.     

A Demographic Profile of Obesity in the Adult and Veteran US Populations in 2008

Obesity is increasing in the US population and seems to be disproportionately burdening disadvantaged groups. Veterans using the Veterans Healthcare System (VHS) tend to be more disadvantaged socioeconomically than the general population and in poorer health. It is important to understand how the veteran population differs from or is similar to the general population and whether the VHS is able to mediate obesity risk among veterans. This research assesses the sociodemographic, behavioral, and health risk factors for obesity in the US adult and veteran populations in 2008. We use data from the 2008 Behavioral Risk Factor Surveillance System (BRFSS) to empirically assess predictors of obesity risk. We find that women have lower odds of obesity than men once controls for sociodemographic, behavioral, and health conditions are included in our models. We also observe a veteran obesity disadvantage in the full adult sample when conducting bivariate tests, but no significant association with the odds of obesity in the logistic regression models among veterans and non-veterans. Gender specific models indicate that male veterans have increased odds of obesity compared to non-veterans, but no difference in obesity risks among veterans and non-veterans are noted for women, controlling for all variables. Further, we find no significant differences in the odds of obesity of veterans using VHS for all, some, or none of their health care needs; further no significant gender differences in obesity risk were observed among VHS usages and non-users. Based on the strong, positive association between the number of chronic health conditions and the odds of obesity, we suggest that health policy should focus efforts on weight management counseling for obese patients that have obesity related co-morbidities, and more targeted attention to male veterans would help to address the high level of obesity in this vulnerable population group.