A Couple-Based Approach to the Reduction of PTSD Avoidance Symptoms: Preliminary Findings

This study reports preliminary findings regarding the feasibility and efficacy of a novel couple-based treatment, named Strategic Approach Therapy (SAT), for reducing avoidance symptoms of posttraumatic stress disorder (PTSD). Six male Vietnam combat veterans diagnosed with PTSD and their cohabitating marital partners participated in 10 weeks of SAT treatment. Self-report, clinician ratings, and partner ratings of PTSD symptoms were obtained before the first session and after the tenth session of treatment. Veterans reported statistically significant reductions in self-reported, clinician-rated, and partner-rated effortful avoidance, emotional numbing, and overall PTSD severity. These data indicate that SAT offers promise as an effective treatment for PTSD avoidance symptoms.     

The Cost of Compensating Asbestos Victims Under the Occupational Disease Compensation Act of 1983

The potentially huge financial liability due to asbestos product suits and the resulting filings for reorganization in bankruptcy by Manville, UNR Industries, Inc., and Amatex, has become a major public policy concern. In response to the problem several bills have been introduced in the Congress to provide compensation for asbestos (and other occupational disease) victims. This paper estimates the cost of compensating asbestos victims under the provisions of the "Occupational Disease Compensation Act of 1983," introduced by Congressman George Miller. Utilizing fatality projections from studies by Enterline, Selikoff, and Walker, and assumptions regarding likely claims filing and success rates, duration and degree of disability, and medical expenses, first year costs for this legislation are estimated to range from a low of $131 million to a high of $ billion. Present value cost estimates at a 2% real discount rate range from $3 billion to $56 billion. The paper also estimates the impact of possible modifications to the compensation provisions of the legislation. Reducing medical payments by the amount received from medicare would lower costs by 3-4%. Providing survivors with a 3-year lump sum benefit rather than a 5-year lump sum payment would save 20-25% as would offsetting the 5-year lump sum by expected social security old age and disability benefits. Combining all of these changes would reduce costs by almost 50%.     

Positive and negative affect: A maximum-likelihood approach

Using the LISREL maximum-likelihood program, the relation between Bradburn's positive affect and negative affect scales is examined for three age groups of adults. It is found that (a) unequal item loadings fit significantly better than equal item loadings; (b) the best-fitting loadings for the elderly are significantly different from those of the non-elderly; (c) the positive and negative affect scales are substantially correlated and (d) correlations with related variables are stronger when positive and negative affect scales are formed by maximum-likelihood loadings rather than by unit loadings. Given the widespread use of Bradburn's scales, implications of these results for subjective well-being are discussed.     

Two Moments of the Logitnormal Distribution

We display the first two moment functions of the Logitnormal(μ, σ²) family of distributions, conveniently described in terms of the Normal mean, μ, and the Normal signal-to-noise ratio, μ/σ, parameters that generate the family. Long neglected on account of the numerical integrations required to compute them, awareness of these moment functions should aid the sensible interpretation of logistic regression statistics and the specification of “diffuse” prior distributions in hierarchical models, which can be deceiving. We also use numerical integration to compare the correlation between bivariate Logitnormal variables with the correlation between the bivariate Normal variables from which they are transformed.     

On a multiple endpoints testing problem

In a clinical trial comparing drug with placebo, where there are multiple primary endpoints, we consider testing problems where an efficacious drug effect can be claimed only if statistical significance is demonstrated at the nominal level for all endpoints. Under the assumption that the data are multivariate normal, the multiple endpoint-testing problem is formulated. The usual testing procedure involves testing each endpoint separately at the same significance level using two-sample t-tests, and claiming drug efficacy only if each t-statistic is significant. In this paper we investigate properties of this procedure. We show that it is identical to both an intersection union test and the likelihood ratio test. A simple expression for the p-value is given. The level and power function are studied; it is shown that the test may be conservative and that it is biased. Computable bounds for the power function are established.     

Gone Missing? Disabled children living away from their families

Many disabled children spend most of their childhood in 'care', but not formally 'in care'. Research concerning disabled children has been dominated by a medical model of disability and by a failure to include the subjective reality of children themselves. There is also inadequate statistical information available concerning children who spend most of their time away from a family setting. The article looks at what we do know about such experiences, identifying some issues for future research.     

Regression Modelling of Disease Risk in Relation to Point Sources

We describe a class of models for the investigation of possible raised risk of disease around putative sources of environmental pollution. An adaptation of the point process method suggested by Diggle and Rowlingson is presented, allowing the use of routinely available aggregated data and incorporating the more general distance–risk model suggested by Elliott and co-workers. An application to data on cancers of the stomach around municipal solid waste incinerators is presented.     

Exponential Family Models for sampled and census Network data

Much progress has been made on the development of statistical methods for network analysis in the past ten years, building on the general class of exponential family random graph (ERG) network models first introduced by Holland and Leinhardt (1981) . Recent examples include models for Markov graphs, "p*" models, and actor‐oriented models. For empirical application, these ERG models take a logistic form, and require the equivalent of a network census: data on all dyads within the network. In a largely separate stream of research, conditional log‐linear (CLL) models have been adapted for analyzing locally sampled ("egocentric") network data. While the general relation between log‐linear and logistic models is well known and has been exploited in the case of a priori blockmodels for networks, the relation for the CLL models is different due to the treatment of absent ties. For fully saturated tie independence models, CLL and ERG are equivalent and related via Bayes' rule. For other tie independence models, the two do not yield equivalent predicted values, but we show that in practice the differences are unlikely to be large. The alternate conditioning in the two models sheds light on the relationship between local and complete network data, and the role that models can play in bridging the gap between them.