A general linear model for estimating effect size in the presence of publication bias

When the process of publication favors studies with smallp-values, and hence large effect estimates, combined estimates from many studies may be biased. This paper describes a model for estimation of effect size when there is selection based on one-tailedp-values. The model employs the method of maximum likelihood in the context of a mixed (fixed and random) effects general linear model for effect sizes. It offers a test for the presence of publication bias, and corrected estimates of the parameters of the linear model for effect magnitude. The model is illustrated using a well-known data set on the benefits of psychotherapy.Authors' note: The contributions of the authors are considered equal, and the order of authorship was chosen to be reverse-alphabetical.     

An investigation of the effects of comorbid Axis II pathology on outcome of inpatient treatment for unipolar depression

DSM-based research on comorbidity has suggested thatdepression andpersonality disorder frequently occur together and that the combination of syndromes is associated with a poor response to treatment for depression. The present study was designed to explore the effect of comorbid Axis II pathology for a sample of 45 inpatients who received treatment for major depression. Both categorical and dimensional ratings of personality disorder were used in the statistical analysis. Positive categorical diagnosis of Cluster C (anxious-avoidant) disorder, as well as higher dimensional rating of Cluster A (odd-eccentric) pathology, was predictive of a poor response to treatment (p<.05), as measured by change in pre-post clinical ratings on the Montgomery-Asberg Depression Rating Scale. These results were construed as indicative of a significant Axis II comorbidity effect in the context of an inpatient, multimodal treatment setting for depression. The results also spotlight the influence of techniques of measurement in determining the outcome of statistical analysis.     

Selective mutism in children: A structural family therapy approach to treatment

When children refuse to speak in some social settings, but can understand and speak in other settings, the diagnosis of selective mutism must be considered. A review of the literature describes the disorder, the various types of mutism, and related family dynamics. A family systems approach to treatment using structural family therapy is suggested. The case history presented illustrates one type of mutism as well as the family rules and hierarchy which appeared to be maintaining it. Structural and strategic family systems theory techniques that were used to move the family toward resolution of this problem are discussed.Diane Wolf Tatem, MA, MS, completed graduate work in marriage and family therapy at New Mexico State University, Las Cruces, NM. She is employed at Life Management Center of El Paso's Child Development Services and also has a private practice in marriage and family therapy in El Paso, Texas. Robert L. DelCampo, PhD is a professor of family science at New Mexico State University and maintains a private practice with Associates for Marriage and Family Therapy in Las Cruces, NM. Please address all correspondence to Dr. DelCampo at Box 3470, New Mexico State University, Las Cruces, NM, 88003-3470.Appreciation is expressed to Dr. Charles Huber, New Mexico State University in Las Cruces, for his insightful critique of the final draft of this paper. This paper was presented at the Texas Association for Marriage and Family Therapy Annual Conference, January 25–29, 1995 in Dallas, TX.     

Differential effects of cognitive behavior modification on seriously emotionally disturbed adolescents exhibiting internalizing or externalizing problems

This study examined the differential effects of a school-based cognitive behavior modification intervention on (a) the interpersonal/social skills and (b) the social competence and school adjustment of two groups of middle school students identified as seriously emotionally disturbed. One groups of students exhibited internalizing emotional problems and the other group exhibited externalizing emotional problems. The objective of the study was to investigate whether the effectiveness of a school-based cognitive behavior modification intervention was significantly related to the type of emotional disturbance a student exhibits (i.e. internalizing or externalizing emotional disturbance). The sample consisted of an experimental and a control group of middle school students identified as seriously emotionally disturbed. The intervention was implemented in 23 biweekly 42-minute sessions. The results indicated that teacher ratings of student social competence and school adjustment were sensitive to treatment effects, although students' social skills self-ratings were not significantly affected by the treatment. A differential treatment effect was established in that externalizing students were significantly more responsive than internalizing students.     

Calibration of sensory and cognitive judgments: A single model for both

In a recent issue of this journal, Winman and Juslin (34 , 135–148, 1993) present a model of the calibration of subjective probability judgments for sensory discrimination tasks. They claim that the model predicts a pervasive underconfidence bias observed in such tasks, and present evidence from a training experiment that they interpret as supporting the notion that different models are needed to describe judgment of confidence in sensory and in cognitive tasks. The model is actually part of the more comprehensive decision variable partition model of subjective probability calibration that was originally proposed in Ferrell and McGoey (Organizational Behavior and Human Performance, 26 , 32–53, 1980). The characteristics of the model are described and it is demonstrated that the model does not predict underconfidence, that it is fully compatible with the overconfidence frequently found in calibration studies with cognitive tasks, and that it well represents experimental results from such studies. It is concluded that only a single model is needed for both types of task.     

An extension of the partial credit model with an application to the measurement of change

The partial credit model is considered under the assumption of a certain linear decomposition of the item × category parameters _ih into basic parameters _j. This model is referred to as the linear partial credit model. A conditional maximum likelihood algorithm for estimation of the j is presented, based on (a) recurrences for the combinatorial functions involved, and (b) using a quasi-Newton approach, the so-called Broyden-Fletcher-Goldfarb-Shanno (BFGS) method; (a) guarantees numerically stable results, (b) avoids the direct computation of the Hesse matrix, yet produces a sequence of certain positive definite matricesB _k ,k=1, 2, ..., converging to the asymptotic variance-covariance matrix of the . The practicality of these numerical methods is demonstrated both by means of simulations and of an empirical application to the measurement of treatment effects in patients with psychosomatic disorders.The authors thank one anonymous reviewer for his constructive comments. Moreover, they thankfully acknowledge financial support by the Österreichische Nationalbank (Austrian National Bank) under Grant No. 3720.     

SEQUENTIAL APPLICATION OF MAJOR HABIT-REVERSAL COMPONENTS TO TREAT MOTOR TICS IN CHILDREN

In this study, we sequentially administered up to four components of the habit-reversal treatment to 4 children with motor tics within a multiple baseline design. The habit-reversal components included (a) awareness training; (b) awareness training and self-monitoring; (c) awareness training, self-monitoring, and social support; and (d) awareness training, social support, and the use of a competing response. Results demonstrated that the combined use of awareness training, social support, and competing response training was effective in eliminating motor tics in 2 of 4 children, that awareness training alone was effective for 1 child, and that a combination of awareness training and self-monitoring was effective for the 4th child. The treatment and ensuing improvement were found to be socially valid. We discuss possible explanations for these results and recommend directions for future research.     

Physical characteristics of residential psychiatric and substance abuse programs: Organizational determinants and patient outcomes

Described the Physical and Architectural Characteristics Inventory (PACI), which assesses the physical characteristics of hospital- and community-based psychiatric and substance abuse residential treatment programs for adults. Developed using data from 94 representative programs, the PACI has 7 dimensions that assess community accessibility, physical features that add convenience, aid recreation, and provide support for patients, and space for patient and staff functions. In comparison to community-based programs (n=63), hospital programs (n=31) had more social-recreational and prosthetic aids, safety features, staff facilities, and space. The PACI dimensions were also related to other organizational features, such as facility ownership and program size and staffing level. Programs with more physical amenities had patients who were more involved in self-initiated and community activities and were more likely to successfully complete the program and be discharged to independent living situations and paid jobs. Programs with more social-recreational and prosthetic aids, space, and access to community resources also had better patient outcomes. In addition, PACI dimensions were related to observers' ratings of facility attractiveness. Potential applications of the PACI and the full inventory of which it is a part are discussed.