It has been over 30 years since Tversky's elimination by aspects (EBA) model was introduced. Despite the potential importance of this elegant model, no method for parameter estimation has emerged. In this paper we prove that simple differences in observed choice probabilities across choice sets are linearly related to the parameters in the EBA model. Once the appropriate probability differences are calculated it is then easy to use widely available least-squares software to estimate the EBA parameters. This paper also corrects a misconception about the number of free parameters in the EBA model. The parameter estimation approach is demonstrated on data from repeated choices of one individual.

BACKGROUND: Although diagnostically homogeneous group therapy is a generally accepted component of the outpatient treatment of persons with bipolar disorder, investigations into the use of this modality in the inpatient setting are preliminary.OBJECTIVES: The purpose of this study was to compare the effectiveness of the Self-Management Group Model with that of the Interactional Group Model in improving the ability of patients hospitalized with bipolar disorder to care for themselves when discharged.DESIGN: This study used a quasi-experimental, nonequivalent comparison group design with repeated measures that were administered before the intervention, after the intervention, and 3 months after discharge from the hospital. Instruments elicited data on self-reported mood states, behavior and symptom identification, coping resources, and satisfaction with the group services.RESULTS: One hundred twenty-two people participated at the first measurement period. No significant total score differences were found between the two groups on any of the four measurements. However, 3 months after hospitalization, Interactional Group Model participants reported significantly less difficulty with behaviors and symptoms at the 3-month measurement period when compared with their admission scores but less satisfaction with the groups than they had at discharge.CONCLUSIONS: Results suggest that each method has advantages; the optimal model may be one that combines elements of both methods within a self-management focus.

This study explored the perceptions of people hospitalized for bipolar disorder in regard to their difficulties in functioning and the most important problem with which they would like the hospital's help. One-hundred-twenty-two patients diagnosed with bipolar disorder completed the Behavior and Symptom Identification Scale (BASIS-32) at the beginning of their hospitalization. The relationships between subjective distress (measured by the BASIS-32 scores) and background characteristics were examined. In addition, participants' perceptions of their most important problems were coded as (1) psychiatric problems, (2) social or physical problems, or (3) no problems, and examined with respect to background characteristics. Race, admission status, and a secondary diagnosis of a substance use disorder were significantly related to overall subjective distress; a substance use disorder diagnosis was significantly related to all five BASIS subscale scores. No background variable was significantly related to the problems with which participants reported wanting the hospital's help, although admission status and race were of borderline significance.

Forty-two African-American and 80 white patients hospitalized for bipolar disorder completed the Coping Resources Inventory. Total resource scores of the African Americans were significantly higher than scores of the whites, although differences in background variables between the two groups were not evident. The African-American group also scored significantly higher than the whites on the three scales indicating internal resources-cognitive, emotional, and spiritual-philosophical, No statistically significant differences were found for the two groups on the social and physical scales. Cultural orientations influencing personal life philosophies may explain the differences between the African-American and white patients on perceptions of their coping resources.

This study assessed whether a secondary diagnosis of a substance use disorder in hospitalized people with bipolar disorder was associated with poorer outcomes on self-reported measures of mood (Profile of Mood States), subjective distress (Behavior and Symptom Identification Scale), and coping resources (Coping Resources Inventory), and with specific patient characteristics. Sixty-two patients with bipolar disorder and a secondary diagnosis of a substance use disorder and 60 patients with only a bipolar disorder diagnosis participated. Patients with bipolar disorder and a secondary diagnosis of a substance use disorder perceived significantly more impairment on all three measures than did patients without the secondary diagnosis. Moreover, the background characteristics of a history of violence, past or current involvement with the criminal justice system, and not having an antipsychotic medication prescribed during hospitalization had the strongest association with having a secondary diagnosis of a substance use disorder among the characteristics examined. These findings suggest the existence of a subgroup of patients with substance abuse and bipolar disorders who have substantial psychosocial impairment and probably require more intense treatment.

The purpose of this study was to (a) compare participants' evaluations of two models of inpatient group therapy for people with bipolar disorder and (b) develop a taxonomy of patient satisfaction with such groups. The sample of 110 people included 59 participants in the self-management groups and 51 participants in the interactional groups. Results indicated that although neither of the models was clearly preferred by participants, the responses were useful in identifying needed changes, and the benefits of providing inpatient diagnostically homogeneous groups for this population were evident. A refined self-management model that incorporates agenda setting in the format, and a taxonomy for use in future research, are presented.