The present study investigates the statistical consequences of attribute misspecification in the rule space method for cognitively diagnostic measurement. The two types of attribute misspecifications examined in the present study are exclusion of an essential attribute (which affects problem-solving performance) and inclusion of a superfluous…

The Q Sort method is a rank order procedure. A FORTRAN program is described which calculates a total value for any group of cases for the items in the Q Sort, and rank orders the items according to this composite value. (Author/JKS)

McQuitty has developed a number of pattern analytic methods that can be computed by hand, but the matrices of associations used in these methods cannot be so readily computed. A simplified but exact method of computing product moment correlations based on Q sort data for McQuitty's methods is described. (Author/JKS)

The G index and its generalizations in the six basic factor analytic designs are discussed. G should be used if there is no mutual direction of all the variables. G should also be used if the scale center is more suitable as a reference point than the mean value. (Author/CTM)

A new measure of similarity between persons applicable in Q-analysis is proposed. It allows assumptions of non-orthogonality between the items, across which the similarity is computed. The similarity measure may also be applied in an R-analysis. (Author/JKS)

Q factor analysis is found appropriate for use in clinical or educational situations where available typologies or scales seem inadequate, where the psychological dynamics of learning or treatment are not well understood, or where it is desirable to avoid anticipating the precise direction and character of program impact. (Author/BJG)

The theoretical expectations of duality of attitude structure and comparative lack of bipolarity have now been found using both R and Q methodologies. (Author)

Test-retest reliability of the Q-Sort Inventory of Parenting Behaviors was obtained with a sample of 30 mothers of 3-year-olds. The within-subject correlation, with 2 weeks between test administrations, for sorting the test statements was 0.72. Reliable differences among the respondents were responsible for 35% of the variance. (SLD)