Replies to an article in "Human Communication Research" (v14, n4), "Item Desirability Effects in Compliance-Gaining Research: Seven Studies Documenting Artifacts" by Brant R. Burleson, Steven R. Wilson, Michael S. Waltman, Elizabeth M. Goering, Teresa K. Ely, and Bryan B. Whaley. (MS)

Finds that, among 214 Canadian college students, subjects with high test anxiety had significantly lower overall scores on the Wisconsin Card Sorting Test (WCST) and experienced greater cognitive interference during the test than subjects with low test anxiety. Groups did not vary significantly, however, on individual WCST variables. (SV)

Results are reported from a study, involving 35 female undergraduates, which examined the correlation between the health of the students, as measured by self-reported incidence of illness and directly observable physiological (blood pressure) measures, and the frequency and perceived stress of examinations and assignments. (IAH)

Based on the division of attained change for each treated individual into causal and noncausal change, the product-moment correlation between causal change and initial level is studied and compared with the correlation between attained change and initial level. Relevant formulas for true scores at population level are presented. (SLD)

Research with couples requires measurement and data analytic techniques extending beyond those typically used with individuals. Measurement issues in couples' research that influence subsequent approaches to data analysis are reviewed, with emphasis on issues of nonindependence in couples' data. Univariate and multivariate analyses of…

Discusses the use of chaos, or nonlinear dynamics, for investigating computer-mediated communication. A comparison between real, human-generated data from a computer network and similarly constructed random-generated data is made, and mathematical procedures for determining chaos are described. (seven references) (LRW)

A survey of 29 employees at a real estate office revealed that one-third still felt incompetent with computers despite generally positive attitudes toward them. A correlation appears to exist between frustration with computers and job satisfaction, although negative attitudes toward computers and job performance appear unrelated to organizational…

Presents new methods for compressing bit matrices in large information retrieval systems which exploit possible correlations between rows of words and columns of documents. Three encoding methods are tested and compared--Shannon-Fano, arithmetic, and Huffman--and an appendix discusses binomial coefficients. (20 references) (LRW)

It is argued that the axes of the Learning Style Inventory and Learning Style Questionnaire are not conceptually aligned. More accurate comparison involves the degree of similar classification of learning styles, as illustrated in the modest but similar degree of classification for 44 graduate and undergraduate students. (SLD)

Three factors that increase score variability yet can be associated with an increase, a decrease, or no change in Pearson's correlation coefficient (r) are discussed (restriction of range, errors of measurement, and linear transformations of data). The connection between changes in variability and r depends on how changes occur. (SLD)

Large sample chi-square tests of the significance of the difference between two correlated kappas, weighted or unweighted, are derived. Cases are presented with one judge in common between the two kappas and no judge in common. An illustrative calculation is included. (Author/SLD)

The internal consistency of a scale and various indices of rating scale response styles (such as halo, leniency, and positive or negative response bias) are related to mean scale item intercorrelation. The consequent relationship between internal consistency and rating scale response styles is discussed. (Author/SLD)

An algorithm for obtaining initial values for the minimization process in covariance structure analysis is developed that is more generally applicable for computing parameters connected to latent variables than the currently existing ones. The algorithm is formulated in terms of the RAM model but can be extended. (SLD)

The difference in effect on power of restriction of range between treatments under experimental control and categories formed from examinee (individual differences) variables is discussed. Conditions under which there is loss or increase of power are explained. (SLD)

Formal relationships are explored among several methods of linearly constrained correspondence analysis. The seven methods considered fall within one of two classes corresponding to ways of imposing linear constraints: the reparameterization method, and the null space method. A connection between these classes is established through a lemma by C.…