Robert G. Demaree

Estimating Within-Group Interrater Reliability with and without Response Bias.

Abstract : This article presents methods for assessing agreement among the judgments made by a single group of judges on a single variable in regard to a single target. For example, the group of judges could be editorial consultants, members of an assessment center, or members of a team. The single target could be a manuscript, a lower-level manager, or a team. The variable on which the target is judged could be overall publishability in the case of the manuscript, managerial potential for the lower-level manager, or team cooperativeness for the team. The methods presented are based on new procedures for estimating interrater reliability. For situations such as the above, these procedures are shown to furnish more accurate and interpretable estimates of agreement than estimates provided by procedures commonly used to estimate agreement, consistency, or interrater reliability. In addition, the proposed methods include processes for controlling for the spurious influences of response biases (e.g., positive leniency, social desirability) on estimates of interrater reliability. (Author)

A National Follow-up Study to Evaluate the Effectiveness of Drug Abuse Treatment: A Report on Cohort 1 of the DARP Five Years Later

Preliminary findings for the first cohort of a national follow-up study of drug users admitted to treatment in the Drug Abuse Reporting Program (DARP) during 1969-1971 are reported. From a sample of 1,853 selected for follow-up, 87% were located and interviews were completed for 77%. Gross tabulations are shown comparing several outcome measures based on pre-DARP treatment, the posttreatment period, and for the 2 months before interview. Sixty-one percent of all patients returned to treatment at some time after DARP termination. Decreases in drug use, expecially of opioids, were substantial and were generally accompanied by improvements in other outcome measures as well. Plans for more detailed and informative analysis of these and related DARP data are addressed.

A statistical rationale for relating situational variables and individual differences

Abstract Statistical rationale is presented for relating situational variables (e.g., technological complexity) to person variables (e.g., environmental perceptions, attitudes). A procedure is described wherein correlations are determined between a person variable and one or more situational variables after the scores on the situational variables have been assigned to individuals. The results of the procedure provide opportunities to ascertain (a) the degree to which variation among individuals on a person variable is associated with situational differences, and (b) the degree to which a situational variable accounts for the total possible variation in the person variable that is associated with between-group differences.

Indicators of Criminality During Treatment for Drug Abuse

Many studies have pointed to a sharp reduction in criminal activities upon entry into drug treatment programs [1, 2], as well as to a generally low ebb of criminal behavior during treatment. The present study sought to add to such findings by taking a close look at several indicators of criminality in a sample of 3483 outpatients who were followed for the first 6 to 12 months in methadone maintenance or drug-free treatment programs at 31 different agencies participating in the Drug Abuse Reporting Program [3]. The data available on each patient, admitted during a one-year period starting June 1, 1971, consisted of an Admission Record and bimonthly status reports.

Respiratory phase and visual signal detection

Previous studies have implicated respiration as a source of intra-S variation in visual signal detection tasks. In the present study, pneumographic respiration records were obtained on 22 female undergraduates during a visual signal detection task. The analysis of signal detection with respect to respiration phase showed that signals presented during exhalation were detected more frequently than those presented during inhalation. These findings suggest that the intra-S variation in signal detection performance may be partially accounted for by respiratory behavior at the moment of signal presentation.

Outcome measurement for drug treatment in the DARP: during-treatment criterion scales.

In summary, it is believed that the index values served quite well as criterion measures, considering the highly skewed distributions of the original data. The index values could be readily interpreted without reference to any statistical distribution, and they lent themselves to the study of levels and patterns of outcomes over time in treatment.

A Note on the Dynamic Correlation Coefficient.

Abstract : The use of the dynamic correlation coefficient as a test of spuriousness in longitudinal designs was examined. It was shown that given conditions of spuriousness and perfect stationarity, the dynamic correlation coefficient was positively, rather than inversely, related to spuriousness. It was recommended that the dynamic correlation coefficient not be used in the future as a test of spuriousness. (Author)

A Critique of Validity Generalization

Validity generalization refers to whether validity coefficients obtained in prior studies in organizational environments may be used to forecast the value of a validity coefficient in a new but similar organizational environment. Validity coefficients obtained in prior situations are “generalizable” if evidence suggests that they may be employed to forecast the magnitude of a validity coefficient in a new situation. Of perhaps greater importance is the belief that a validation analysis may not be required in the new situation if evidence for validity generalization is extensive. Conversely, a “local” or “situationally specific” validation analysis in the new situation would be required if evidence for validity generalization is unavailable or if the existing evidence suggests a lack of generalization.

Saul B. Sells (1913-1988).

ISSN: 0027-3171 (Print) 1532-7906 (Online) Journal homepage: http://www.tandfonline.com/loi/hmbr20 Saul B. Sells (1913-1988) Robert G. Demaree & Stanley A. Mulaik To cite this article: Robert G. Demaree & Stanley A. Mulaik (1988) Saul B. Sells (1913-1988), Multivariate Behavioral Research, 23:3, 294-296, DOI: 10.1207/s15327906mbr2303_1 To link to this article: http://dx.doi.org/10.1207/s15327906mbr2303_1