The use of simple reparameterizations to improve the efficiency of Markov chain Monte Carlo estimation for multilevel models with applications to discrete time survival models

Summary.  We consider the application of Markov chain Monte Carlo (MCMC) estimation methods to random-effects models and in particular the family of discrete time survival models. Survival models can be used in many situations in the medical and social sciences and we illustrate their use through two examples that differ in terms of both substantive area and data structure. A multilevel discrete time survival analysis involves expanding the data set so that the model can be cast as a standard multilevel binary response model. For such models it has been shown that MCMC methods have advantages in terms of reducing estimate bias. However, the data expansion results in very large data sets for which MCMC estimation is often slow and can produce chains that exhibit poor mixing. Any way of improving the mixing will result in both speeding up the methods and more confidence in the estimates that are produced. The MCMC methodological literature is full of alternative algorithms designed to improve mixing of chains and we describe three reparameterization techniques that are easy to implement in available software. We consider two examples of multilevel survival analysis: incidence of mastitis in dairy cattle and contraceptive use dynamics in Indonesia. For each application we show where the reparameterization techniques can be used and assess their performance.     

Explaining gender segregation

Occupational gender segregation--the tendency for women and men to work in different occupations--is an important feature of all societies, and particularly the wealthy industrialized ones. To understand this segregation, and to explain its significance, we need to distinguish between vertical segregation entailing inequality and horizontal segregation representing difference without inequality, with overall segregation being the resultant of these components. Three major theoretical approaches to understanding occupational gender segregation are examined: human capital/rational choice, patriarchy, and preference theories. All are found to be inadequate; they tend to confuse overall segregation with its vertical component, and each entails a number of other faults. It is generally assumed or implied that greater empowerment of women would reduce gender segregation. This is the reverse of what actually happens; in countries where the degree of women's empowerment is greater, the level of gender segregation is also greater. An alternative theoretical approach based on processes of social reproduction is shown to be more useful.     

An Empirical Investigation of Web Site Use Using a Commitment‐Based Model

Companies throughout industry are interested in retaining existing customers, because customers' continuous consumption of products and services is critical to the long‐term value propositions of most organizations. Thus, decision‐making strategies that promote continuous use and customer retention are of research interest, both theoretically and practically. In the present research, we investigate one important area of continuous usage, that of Web site use. In particular, we use several theories of commitment to understand how an individual's decision to continue to use a Web site is influenced by his or her commitment toward that Web site and the vendor that supports it. Results derived from data collected from 335 users of a variety of Web sites indicated that affective commitment, calculative commitment, quality of alternatives, and trust were significantly associated with an individual's behavioral intention to continue to use a Web site. Implications for customer retention and decision‐making strategies are discussed.     

A Study of An Alternative School for Pregnant and/or Parenting Teens: Quantitative and Qualitative Evidence

In response to multiple problems faced by pregnant and parenting teens, many alternative school-based comprehensive programs have been established throughout the United States. By collecting data from a sample of enrollees of such a school-based comprehensive program and comparing them with data collected from a sample of non-enrollees, the present study systematically evaluates the program. The results of the study seem to suggest that the program participants were more likely to have higher educational aspiration, better reproductive health outcomes, higher contraceptive use, and more breast-feeding practice and intention than those of their non-participating counterparts. The implications of the study findings for comprehensive school-based program for pregnant and/or parenting teens are discussed.Ruhul Amin is a Senior Fellow at the Center for Health Disparities Solutions and Senior Research Scientist in the Institute for Urban Research, Morgan State University, Baltimore, MD 21239. Dorothy C. Browne is the Director of the Institute for Urban Research, Jamir Ahmed is a research assistant at the Center for Health Disparities Solutions and Takanori Sato is research assistants at the Institute for Urban Research, Morgan State University, Baltimore, MD 21239.     

The assessment of drawings from children who have been maltreated: a systematic review

This paper presents a systematic review that aims to identify studies using drawing techniques with maltreated children. The paper first introduces the relevant developmental theory relating to children's drawings and its application to practice. Studies using drawing techniques with maltreated children were identified from both the research and practice literature. These were summarized and compared. The evidence from the studies appears relatively inconclusive as to the value of children's drawings for the identification of possible maltreatment, although they do apparently help in aiding recall of important events. Drawings are widely used to assess maltreatment and neglect of children. However, researchers advocate caution in generalizing and interpreting drawings from children with differing experiences. Copyright © 2002 John Wiley & Sons, Ltd.