Poisson models for assessing rater agreement in discrete response studies

In this paper we discuss a method for assessing agreement among raters who are scoring the number of times, a specified event occurs. In such cases, it seems reasonable to define agreement in terms of raters' behaviours in correctly identifying responses which have in fact occurred, and in their falsely counting responses which have not. We exploit the discrete nature of the response variable, and examine a class of models for mean response assuming an underlying Poisson distribution. Test statistics are given for deciding on the applicability of the models, and whether there is agreement with respect to correctly detecting responses, as well as with falsely scoring responses.     

SEX DIFFERENCES IN THE ATTRIBUTION OF SOCIALLY DESIRABLE AND UNDESIRABLE TRAITS TO OUT-GROUP MEMBERS*

One hundred and forty-four male and female Australian subjects rated an Australian or a Vietnamese target group on the possession of five socially desirable and five socially undesirable personality traits. As predicted, the out-group was perceived less favourably than the in-group, but only by the males, the females not making the distinction.     

Stability of magnitude production scales for oral and nonoral vibrotactile mechanoreceptive systems

The stability of oral and nonoral vibrotactile magnitude scales produced by the method of magnitude production was investigated for 11 adult subjects. Each subject was tested over four sessions separated by 1-wk. intervals. Data analyses included correlations across trials of power function slopes as well as individual adjustments of intensity. Analysis showed a lack of stability over time for the slope functions obtained on the thenar eminence but moderate stability for the functions obtained on the tongue. Individual adjustments on intensity showed consistently high correlations across trials and structures. It was concluded that the subjects' responses were guided by the imposed experimental variables and that each individual's scaling was not necessarily reflected by the correlations based on power function slopes established over the four trials.     

Participation,influence, and satisfaction in group decision making

The hypothesis that attitudinal effects of participation depend on individual differences in motivation was tested in a laboratory experiment with 56 three-man groups (leader and two members). Measures of the attractiveness of power and social acceptance were obtained prior to a group decision task, after which members described their perceived participation, influence, and satisfaction. Results showed that: (a) influence was more strongly related to satisfaction for members with strong, as opposed to weak, power motives; (b) for members with strong affiliation motives, participation was more strongly related to satisfaction than was influence. Relationships varied across satisfaction aspects. It was concluded that participation may be associated with favorable role attitudes through different motive-attainment mechanisms in the group decision-making process.