Assessing measurement equivalence across rating sources: a multitrait-multirater approach

Research examining the structure of multisource performance ratings has demonstrated that ratings are a direct function of both who is doing the rating (rating source) as well as what is being rated (performance dimension). A separate line of research has focused on the extent to which performance ratings are equivalent across sources. To date no research has examined the measurement equivalence of multisource ratings within the context of both dimension and rating source direct effects on ratings. We examine the impact of both performance dimension and rating source as well as the degree of measurement equivalence across sources. Results indicate that (a) the impact of the underlying performance dimension is the same across rating sources, (b) the impact of rating source is substantial and only slightly smaller than the impact of the underlying performance dimension, and (c) the impact of rating source differs substantially depending on the source.     

A response Consistency statistic for the millon clinical multiaxial inventory (MCMI)

Response style in objective psychological testing is an important issue in the reliability and validity of tests as well as in the interpretation of test results. The MCMI provides two response-style indices, the validity scale and the weight factor. The present work presents an additional statistic to assess random response in subjects. The Consistency Coefficient is the correlation between the subjects' endorsement of even and odd items across the 20 MCMI scales. The distributions of 500 patient and 500 randomly generated profiles were compared. Good separation between these distributions was found. The subject data were extremely negatively skewed, whereas the randomly generated data were normally distributed. Data are presented that display positive and negative predictive values, as well as sensitivity and specificity across ranges of prevalence and cut score. These data facilitate the identification of subjects who respond to the MCMI in a random manner so that their scores can be interpreted accordingly.     

‘Undesirable’ and ‘desirable’ shifts in children's responses to repeated questions: age differences in the effect of providing a rationale for repetition

This study examined factors influencing children's tendency to shift responses when questions are repeated within an interview. Forty nine 4–5‐year‐olds and 40 7–8‐year‐olds were questioned about a video they had seen, with questions repeated by the same or a different interviewer. Half the children were given a rationale for question repetition, and half were not. Overall, the older children shifted less than the younger children, and, unlike the younger children, more to misleading than unbiased questions. The rationale did not affect overall shifting, but reduced the probability of ‘undesirable’ shifts (towards inaccuracy) in the younger children, and increased ‘desirable’ shifts (towards accuracy) at both ages. In the younger children, the rationale reduced total number of shifts, but only with the same interviewer, while in the older children the reverse applied. The results suggest developmental progression in the relative contributions of memorial and social/motivational factors to shifting. Implications for investigative interviewing with children are discussed. Copyright © 2004 John Wiley & Sons, Ltd.     

Evaluation of a Brief Group Based Psychological/Educational Treatment Programme for Women with an Iatrogenic Chronic Hepatitis C Virus Infection

Thirty-two women with an iatrogenic chronic hepatitis C virus (HCV) infection were assigned to a treatment or waiting list control group and completed the SF-36, GHQ30, Battles SE, and two in-house questionnaires. A series of mixed model ANOVAs indicated a significant Group × Time effect for SF-36 physical functioning (F = 9.01, p < .01) and a series of repeated measures ANOVAs (treatment group only) indicated a significant time effect for a sustained improvement in psychological well-being (F = 8.01, p < .01) at 3 months posttreatment. Furthermore, most women posttreatment felt more positive and informed about their illness, had more confidence, and reported a greater ability to control and cope with their lives. Psychological/educational treatment programmes show promise for increasing adjustment and coping in women with an iatrogenic HCV infection and may be modified for use in other HCV cohorts.     

A daily diary investigation of self-reported alcohol-related direct and indirect aggression

Research supports the relationship between alcohol use and direct aggression, however, scant research has examined the association between alcohol use and indirectly aggressive behavior. Further, extant research has relied on retrospective reporting of behaviors, which may be subject to recall bias. The daily diary methodology enables the assessment of both the between- and within-subject variation, as well as reduces the likelihood of biased reporting. Consequently, the current study utilized a daily diary design to examine (a) associations between daily alcohol use and alcohol-related aggressive behaviors (i.e., direct and indirect); and (b) the co-occurrence of alcohol-related direct and indirect aggression. Participants were 105 (80% female) college student drinkers. Students completed baseline questionnaires and up to 14 consecutive, daily surveys regarding their previous day alcohol use, alcohol-related direct aggression, and alcohol-related indirect aggression. Findings revealed that alcohol use was associated with same day alcohol-related direct and indirect aggression, after controlling for baseline alcohol use. Self-reported alcohol-related direct aggression was more likely to occur on days in which self-reported alcohol-related indirect aggression occurred, after controlling for dispositional aggression, trait self-control, and baseline alcohol use. Results of the study suggest that, similar to alcohol-related direct aggression, alcohol use is associated with an increased likelihood of alcohol-related indirect aggression. Further, the co-occurrence of alcohol-related indirect and direct aggression supports that individuals may be engaging in multiple types of aggressive behaviors. Findings extend previous cross-sectional and qualitative research suggesting that indirect aggression may co-occur, perhaps increasing in severity.