Multidimensional scaling (MDS) a highly reliable measurement technique, often requires an overwhelming task of the subject in the data collection procedure. This investigation was designed to determine the loss of precision in solution associated with five degrees of systematic reduction in the data collection task. Data were simulated via Monte…

Five separate multidimensional scaling analyses with measurement occasions varying from election day to about 14 months after, resulted in two stable dimensions of political perception. These dimensions were identified as Republican and Democratic evaluative dimensions. The publicity surrounding Watergate apparently did not affect the stability of…

Generalizations of the G index as a measure of similarity between persons beyond the dichotomous situation are discussed. An attempt is made to present a generalization that does not require dichotomization of the items for cases where the number of response alternatives may differ. (Author/JKS)

A Monte Carlo study was carried out to investigate the ability of the ALSCAL multidimensional scaling program to recover true structure inherent in simulated proximity data. The results under varying conditions were mixed. Practical implications and suggestions for further research are discussed. (Author/JKS)

An algorithm for assessing the correspondence of one or more attribute rating variables to a symmetric matrix of dissimilarities is presented. It is useful as an alternative to fitting property variables into a multidimensional scaling space. The relation between the matrix and the variables is determined by evaluating pairs of pairs relations.…

A method is presented whereby discrete occupational titles can be represented along a multidimensional continuum reflecting a population's shared perceptions. Their locations on the continuum are used to identify significant others' influence and vocational preferences. The model is shown to be useful for explicating the processes by which…

Reexamined findings of Thompson, Hatchett, and Phillips (1981) which found that females gave more extreme affect ratings and less extreme control ratings to interpersonal verbs than did males. Used multidimensional scaling techniques with 43 female and 39 male college students. Analyses of data failed to replicate findings of sex differences on…

Describes experiment designed to illustrate the potential of multidimensional scaling (MDS) in illustrating the perceptions of those in a group regarding one another, specifically of coalitions. Participants were 35 students enrolled in a graduate business course. Suggests positive results of the exploratory research show MDS holds promise as an…

This study examines demands placed on evaluators by the Joint Committee on Educational Evaluation's standards. Twenty-two experts in evaluation rated the compatibility of implementing pairs of standards or rated individual standards on a series of scales. Multidimensional scaling revealed five demands of ethical practice. (JAZ)

Reports results of experiment to determine whether mental models are constructed of interrelationships and cross-relationships of character attributions drawn in themes of novels and films. The study used "Animal Farm" in print and cartoon forms. Results demonstrated validity of multidimensional scaling for representing both media.…

Presented data that question the ability of both unidimensional masculinity-femininity scales and bidimensional scales to assess comprehensively the multiple factors of sex role identification (N=207). Data supported a multidimensional approach that brings together the reliable factors in both types of scales and provides the possibility of…

A model for the analysis of paired comparison data is presented which is metric, mathematically tractable, and has an exact algebraic solution. (Authors/MB)

This study investigates four widely used methods of collecting direct similarity judgments for nonmetric multidimensional scaling: rating scale, triads, rank order of pairs, and conditional rank order. (Author/PN)

Alternating least squares and optimal scaling are presented as two approaches to the quantitative analysis of qualitative data. A variety of statistical approaches to this problem are discussed. Three examples are presented. (JKS)

The coincidence hypothesis predicts that dissimilarity between objects that differ on two separable dimensions is larger than predicted from their unidimensional differences on the basis of triangle inequality and segmental additivity. The coincidence hypothesis was supported in two-dimensional stimuli studies. (Author/CM)