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.     

Beliefs About Others’ Perceptions—Gender Typicality: Scale Development and Relationships to Gender Nonconformity,Sexual Orientation,and Well-Being

The purpose of this study was to develop a measure of “other-perceived” gender typicality and test its relationship with gender nonconformity, sexual orientation, and psychological distress. Data on these variables were collected from 632 participants (142 heterosexual men, 77 gay men, 50 bisexual men, 174 heterosexual women, 85 lesbian women, and 104 bisexual women). We designed a Beliefs About Others’ Perceptions—Gender Typicality (BOP-GT) scale on which participants reported how masculine or feminine they thought other people perceived their gendered behavior, interests, appearance, and activities. Factor analysis identified five factors: appearance, emotional response, sporting interests, occupational interests, and interpersonal style. Recalled childhood gender nonconformity (CGN) was significantly associated with each BOP-GT subscale. Heterosexual men rated that other people perceived them to be more masculine scoring on the BOP-GT compared to heterosexual women. Gay men and lesbian women showed cross-sexed patterns on the BOP-GT total scale, appearance, emotional response, and sporting interests scores. Bisexual men and women were generally no different from the other male and female groups, respectively. Bisexual women had greater distress scores, and the BOP-GT emotional response subscale was associated with somewhat greater distress scores. The BOP-GT measure may have use in future research on understanding gendered self-concepts.     

AN ALTERNATING LEAST-SQUARES PROCEDURE FOR ESTIMATING MISSING PREFERENCE DATA IN PRODUCT-CONCEPT TESTING*

Product-concept testing is a popular activity in marketing research. Often the number of new product/service concepts under study far exceeds the time available for any single respondent. Respondents therefore may receive only a subset of the concepts comprising the total design. Researchers are interested in making plausible imputations for the missing evaluations of any given respondent. This paper proposes a model and an iterative estimation procedure to impute missing entries for each evaluator. The model and the procedure incorporate (1) the internal structure of the response matrix and (2) an ancillary matrix of (nonmissing) respondent background data; they also (3) allow for individual differences in respondents' uses of the numerical rating scale. The model is applied to both real and synthetic data. Suggestions also are given on how the data imputations may be used in market segmentation and product-line decisions.     

Nonparametric estimation of regression models with mixed discrete and continuous covariates by the K-nn method

In this article we consider the problem of estimating a nonparametric conditional mean function with mixed discrete and continuous covariates by the nonparametric k-nearest-neighbor (k-nn) method. We derive the asymptotic normality result of the proposed estimator and use Monte Carlo simulations to demonstrate its finite sample performance. We also provide an illustrative empirical example of our method.     

Heart disease risk perception in college men and women

The authors sought to assess the perception of risks for coronary heart disease (CHD) in college men and women. They surveyed 470 undergraduates from 2 major 4-year institutions who completed a questionnaire that measured perceived risks for heart disease. Sixty-eight percent of the respondents rated their risks as lower or much lower than those of their peers, indicating a clear optimistic bias. The research also revealed that the students who exercised regularly rated their risk of coronary disease lower than those who did not do so. In addition, women perceived a number of risk markers to be more potent or causative factors than men did. A significant number of participants did not comprehend commonly understood causal relationships associated with heart disease risk. The findings in this preliminary investigation suggest that college men and women do not accurately perceive their risks for developing heart disease.     

Smoking reduction & cessation: a hospital based survey of outpatients' attitudes

1. Most people with mental illnesses have made at least one attempt to quit smoking on their own. 2. Psychiatric diagnosis and degree of nicotine dependence do not appear to be predictive of ability to quit. 3. People with mental illnesses are aware of nicotine replacement therapy (NRT), but do not combine it with a behavioral program, possibly contributing to the higher rates of recidivism in this population. 4. The lack of participation of mental health care providers in promoting smoking cessation is a complex issue.     

LEARNING TO "THINK SYSTEMS": FIVE WRITING ASSIGNMENTS

This paper describes five highly structured writing assignments for teaching family therapy trainees to think in systems terms: 1) Analysis of a communication task; 2) Family assessment report; 3) Family treatment plan; 4) Analysis of a marital or family therapy interview; and 5) Family autobiography. The overall training context in which the assignments are given and ways to prepare students for the assignments are also discussed.     

When approved is not enough: development of a supervision consultation model

The dramatic increase in the literature that addresses family therapy training and supervision over the last decade has been predominantly in the area of theory, rather than practice. This article describes the development of a meta-supervisory learning context for approved supervisors and provides examples of interactions between supervisors that subsequently influenced both therapy and supervision. We delineate the assumptions that inform our work and offer specific guidelines for supervisors who wish to implement a similar model in their own contexts. We provide suggestions for a proactive refiguring of supervision that may have profound effects and benefits for supervisors and supervisees alike.