No abstract

The performance of the Mantel-Haenszel oddsratio estimator and XI significance test were investigated using simulated data. Multiparameter logistic item response theory models were used to generate item scores for 20-and 40-item tests for 500 reference group and 500 focal group examinees.The difficulty, discrimination, and guessing parameters, and the difference in the group trait level averages were varied and combined factorially. Within each cell of the design, 200 replications were completed under both differential item functioning (DIP) and no-Dip conditions. The empirical 2 Type I and Type 11 error rates, and the average of the odds-ratio estimates, were analyzed over the 200 replications. Under r~c~-z~m conditions, inflated X2 Type I error rates and misestimated odds-ratio values were found for the 20-item test and resulted from interactions between item parameter values and trait differences. For the 40-item test, Type I error rate inflation disappeared but odds-ratios still were misestimated. Under DIF conditions, Type 11 error rates were not inflated, but oddsratios were misestimated, due to parameter x trait level interactions for both test lengths. The results demonstrate the importance of using both the oddsratio and the significance test in interpreting the presence or absence of DIF. In addition, the accuracy under the DIF conditions depended on the size and uniformity Of DIF.

No abstract

Background Previous studies have indicated that persons with co-occurring mental health and substance use problems can benefit by attending dual-focus mutual aid groups. However, to date, a trial to test the efficacy of these groups has not been published. Method This study randomly assigned 203 substance misusing clients attending a mental health or dual-diagnosis facility to either a dual-focus 12-step group (Double Trouble in Recovery; DTR) or a waiting list control group. Participants were followed for 3–6 months. The primary outcome was substance use (days used in the past 30 with saliva testing to detect under-reporting); secondary outcomes included psychiatric medication adherence, attendance at traditional (single-focus) 12-step meetings (e.g., AA/NA); and improvement in mental health and substance use problems (quality of life). Multilevel model (MLM) regression was used to analyze the nested effect of participants within 8 facilities (7 in New York City and 1 in Michigan). Regression imputation was used to adjust for drug use under-reporting. Results At follow-up 79% of the subjects were interviewed. In intent to treat analysis, DTR subjects compared with control subjects used alcohol (p=.03) and any substances (p=.02) on fewer days. DTR compared with control subjects were also more likely to rate themselves as experiencing better mental health and fewer substance use problems (p=.001). There were no effects for DTR on drug use only, medication adherence or NA/AA attendance. Conclusion Findings reported in previous studies on the association between exposure to DTR and reductions in substance use were partially supported in this efficacy trial.

The objective of this study was to acquire process information, clinician and client feedback during implementation of a routine suicide risk screening program for outpatients with serious mental disorders. We studied implementation of a suicide-screening tool in a large public mental health outpatient facility in New York City. Most clinical staff who provided an opinion indicated screening was useful, feasible and helpful; most clients did not mind screening. Facilitators to program implementation included administrative support and ease of use. Barriers included consent, misperceptions, and concerns regarding potential liability. It is feasible to implement a suicide-screening tool in a public outpatient clinic. However, even experienced clinicians harbor unfounded myths. Effective large scale use will require vigorous training and oversight.