Theoretical Medicine and Bioethics Index to Volume 20

Volume Contents

heoretical Medicine and Bioethics Index to Volume 20     

Bayesian estimation and testing of structural equation models

The Gibbs sampler can be used to obtain samples of arbitrary size from the posterior distribution over the parameters of a structural equation model (SEM) given covariance data and a prior distribution over the parameters. Point estimates, standard deviations and interval estimates for the parameters can be computed from these samples. If the prior distribution over the parameters is uninformative, the posterior is proportional to the likelihood, and asymptotically the inferences based on the Gibbs sample are the same as those based on the maximum likelihood solution, for example, output from LISREL or EQS. In small samples, however, the likelihood surface is not Gaussian and in some cases contains local maxima. Nevertheless, the Gibbs sample comes from the correct posterior distribution over the parameters regardless of the sample size and the shape of the likelihood surface. With an informative prior distribution over the parameters, the posterior can be used to make inferences about the parameters underidentified models, as we illustrate on a simple errors-in-variables model.We thank David Spiegelhalter for suggesting applying the Gibbs sampler to structural equation models to the first author at a 1994 workshop in Wiesbaden. We thank Ulf Böckenholt, Chris Meek, Marijtje van Duijn, Clark Glymour, Ivo Molenaar, Steve Klepper, Thomas Richardson, Teddy Seidenfeld, and Tom Snijders for helpful discussions, mathematical advice, and critiques of earlier drafts of this paper.     

The Identity Status Approach: In Need of Fundamental Revision and Qualitative Change

This article is a response to the commentaries of Waterman (this issue) and Berzonsky and Adams (this issue) on my review of the identity status field (van Hoof, this issue). The commentaries illustrate that the identity status researchers attribute different meanings to the identity statuses and identity status research; while Waterman finds it difficult to recognize the field in my review, Berzonsky and Adams agree with several of my conclusions. The two commentaries represent two pillars on which the status approach rests. The difference between the review and the commentaries is that the first includes both pillars, whereas each commentary consists primarily of a selective presentation of assumptions and data. This response focuses on two main points of the commentaries: (a) are the statuses sufficiently validated? and (b) to what extent are they suitable for testing developmental identity hypotheses? Using specific examples I show that the line of reasoning in the commentaries and the data proposed in support of these arguments in fact often support the conclusions of my review, for I demonstrate that the statuses are insufficiently validated and that the statuses are unsuitable for measuring identity development. These conclusions call for a fundamental revision of the identity status approach and a qualitative change in identity theory and research. Finally, the alternative approaches presented by Berzonsky and Adams are evaluated with respect to their contribution to an indispensable qualitative change in the identity status field.     

Developmental sequences in the age of onset of disruptive child behaviors

Retrospective and prospective reports of the onset of disruptive child behaviors were analyzed in a sample of clinic-referred boys. The younger boys (ages 7–9 years), compared with the older boys (ages 10–12 years), showed the highest level of disruptive behavior and, judging from mothers' reports, had the fastest progression of onsets from less serious to more serious problem behaviors. Despite some overlap, developmental sequences in problem behavior within the domains of hyperactivity/inattention, oppositional behavior, and conduct problems were similar across the two age groups. This was also the case for developmental sequences of overt or confrontive problem behaviors and covert or concealing conduct problems. Sequences of the onset of oppositional behavior and conduct problems were validated through prospective data, based on the information from mothers, teachers, and boys themselves. The implications of the findings are discussed for the formulation of developmental pathways of behavior and the analysis of causal factors.     

THE SHIFT IN POWER WITH AGE Changes in Perception of the Power of Women and Men Over the Life Cycle

Previous research has described an apparent shift in perceived interpersonal power towards equality between men and women later in life. This study investigated (a) whether the shift in power with age would appear in the Israeli kibbutz, (b) the role of the parental emergency in the shift, and (c) whether changes in behaviors or attitudes best account for the shift. One hundred twenty younger and older Israeli women and men, half from the city and half from the kibbutz, wrote TAT stories, which were then rated for overall power of the female and male characters, their power strategies, and their motives. A shift in perceived power with age was found in both the city and the kibbutz. Parental status reduced the power of the woman and increased the power of the man only in the city, whereas the reverse was true in the kibbutz. These results counter the parental emergency explanation for the shift in power with age. Furthermore, older women used traditionally feminine power strategies, but their behavior was evaluated as more powerful than the same behavior in younger women. Thus, it is not the behaviors but rather people's evaluation of the behaviors that changes across the life span of the individual.