Non-linear regression models for Approximate Bayesian Computation

Approximate Bayesian inference on the basis of summary statistics is well-suited to complex problems for which the likelihood is either mathematically or computationally intractable. However the methods that use rejection suffer from the curse of dimensionality when the number of summary statistics is increased. Here we propose a machine-learning approach to the estimation of the posterior density by introducing two innovations. The new method fits a nonlinear conditional heteroscedastic regression of the parameter on the summary statistics, and then adaptively improves estimation using importance sampling. The new algorithm is compared to the state-of-the-art approximate Bayesian methods, and achieves considerable reduction of the computational burden in two examples of inference in statistical genetics and in a queueing model.     

Caregiver Emotional Expressiveness,Child Emotion Regulation,and Child Behavior Problems among Head Start Families

The present study examined the relationships between caregivers' self‐reported positive and negative emotional expressiveness, observer assessments of children's emotion regulation, and teachers' reports of children's internalizing and externalizing behaviors in a sample of 97 primarily African American and Hispanic Head Start families. Results indicated that higher caregiver negativity and lower child emotion regulation independently predicted more internalizing behavior problems in children. Additionally, children's externalizing behavior problems were negatively predicted by caregivers' self‐reports of positive emotional expressiveness. Importantly, results also suggested that caregivers' emotional expressiveness and children's behavioral problems may be non‐linearly related, and that child gender may play an important moderating role. These results emphasize the importance of family emotional climate and child emotion regulation in the behavioral development of preschool‐age children, and highlight the need for improved theoretical and practical understanding of socioemotional development in diverse populations.     

Approximate Bayesian Computation for Exponential Random Graph Models for Large Social Networks

We consider the issue of sampling from the posterior distribution of exponential random graph (ERG) models and other statistical models with intractable normalizing constants. Existing methods based on exact sampling are either infeasible or require very long computing time. We study a class of approximate Markov chain Monte Carlo (MCMC) sampling schemes that deal with this issue. We also develop a new Metropolis–Hastings kernel to sample sparse large networks from ERG models. We illustrate the proposed methods on several examples.     

Tournaments as a Worker Discipline Device

This article explores the macroeconomic implications of tournaments as a worker discipline device in the vein of shirking models. It is shown that, if the full exploitation of tournaments is feasible, there will be no involuntary unemployment. Thus, as far as the elimination of involuntary unemployment is concerned, tournaments can serve as a perfect substitute for the so-called "employment fee" or "bonding" scheme. An immediate corollary of this finding is that the involuntary nature of unemployment must ultimately rely upon impediments that hinder the full exploitation of tournaments.     

Examining the structure of awareness and perceptions of groundnut aflatoxin among Ghanaian health and agricultural professionals and its influence on their actions

This study uses a modified health belief model (HBM) within a socio-economic framework to evaluate the influence of awareness and knowledge on actions to reduce aflatoxin (AF) contamination in groundnuts (peanuts). Data were collected in 2002 through a self-administered questionnaire from a sample of 367 individuals. Socio-economic factors affecting perceptions, awareness, knowledge, and action were examined using structural equation modeling. The perceived benefits of good quality groundnuts and/or groundnut products were the most important determinants of awareness and knowledge of AF among agricultural and health professionals in Ghana. Awareness, in turn, had a significant causal effect on the professionals’ decisions to take actions to increase the level of awareness of AF in the society. Demographic factors, such as gender and level of education significantly influenced knowledge of AF and the perception of the benefits of good quality groundnut. Type of profession had a significant influence on awareness and perceived seriousness of the AF problem. Education was a significant determinant of awareness of AF in groundnuts. The study generates important information for policy decision making when considering resource allocation to reduce food contamination in developing economies.     

Using simulation methods for bayesian econometric models: inference,development and communication: some comments

We extend the average derivatives estimator to the case of functionally dependent regressors. We show that the proposed estimator is consistent and has a limiting normal distribution. A consistent covariance matrix estimator for the proposed estimator is provided.     

A generalized negative binomial and applications

A generalized negative binomial distribution is derived from the Markov Bernoulli sequence of successes and failures. We study the properties and applications of this distribution. The properties are illustrated by two examples of discrete time queueing systems. The distribution is then fitted to two data sets, the eruption record of Mt. Sangay, and a record of computer disk failure accesses. In the first case there is a strong serial dependence in the data and the generalized negative binomial provides a good fit, while in the second case, although there is a significant serial dependence, it is insufficient to justify the additional parameter of the distribution. We conclude by demonstrating the usefulness of the distribution in the field of statistical quality control.     

A Qualitative Analysis of College Women's Leaving Processes in Abusive Relationships

Abstract

Objective: This study assessed the process of leaving an abusive dating relationship utilizing a qualitative design. Methods: Participants included 123 college women in abusive dating relationships who participated at the beginning and end of a 10-week academic quarter. Results: Qualitative content analyses were used to analyze the transcribed responses to an open-ended question about women's leaving processes over the interim period. A variety of categories and themes emerged for women in different stages of the leaving process, consistent with the Transtheoretical Model of Change and Investment Model. Data also underscored women's lack of acknowledgment, minimization, and normalization of abuse. Conclusions: These data demonstrate the importance of dating violence intervention and prevention programming on college campuses and offer information that may be useful to college health providers who assist women in abusive dating relationships.     

Testing non-oblique hypotheses

This paper considers a likelihood ratio test for testing hypotheses defined by non-oblique closed convex cones, satisfying the so called iteration projection property, in a set of k normal means. We obtain the critical values of the test using the Chi-Bar-Squared distribution. The obtuse cones are introduced as a particular class of cones which are non-oblique with every one of their faces. Examples with the simple tree order cone and the total order cone are given to illustrate the results.