Virtually all parametric statistical procedures have been shown to be special cases of canonical correlation analysis. This article proposes a logic for conducting stepwise canonical correlation analyses, based upon evaluation of canonical communality coefficients. The procedure is a direct analogue of stepwise multiple regression. (Author/RD)

For multi-subject experiments with all factors repeated (a single independent group of subjects), three multi-subject behavior functions are identified and analyzed. They are based on Shine's actualized and pure single-subject behavior functions extended to multi-subject experiments with some factors nonrepeated (several independent groups of…

Discusses the problem of dichotomous-dependent variables in regression analysis in student attrition studies. Proposes a new method as an alternative to regression analysis. (Author/RC)

Results show that the proposed sampling distribution of the test appears to be appropriate only for sample sizes above 50, and for data where the sample size is 10 times the number of variables. For such cases the power of the test is found to be fairly low. (Author/RL)

Explores relationships between cooperative education work experiences and subsequent benefits. A literature review is followed by a report of data from a survey designed to discover which internship processes are the best predictors of desired outcomes. (CT)

The use of analysis of covariance in conjunction with the multivariate approach to analyzing repeated measures designs is considered for designs involving between- and within-subject factors, one dependent variable, and one observation per subject on the covariate. (Author/RL)

The use of general linear regression methods for the analysis of categorical data is recommended. The general linear model analysis of a 0,1 coded response variable produces estimates of the same response probabilities that might otherwise be estimated from frequencies in a multiway contingency table. (Author/CTM)

Using data from the Current Population Survey and a multivariate approach, compared living arrangements of immigrant children to those of U.S.-born white children with U.S.-born parents. Findings show the "downward assimilation" among some second- and third-generation immigrant children fits a theory of segmented assimilation. Discusses…

Studied the reliability and convergent validity for 27 composite scales and 2 items covering aspects of alcohol use, smoking, marijuana use, and other drug use. Results indicate 23 of the 27 composite scales had at least acceptable reliability and the remaining 4 scales had at least marginally acceptable reliability. At least moderate construct…

Canonical weights and structure correlations are used to construct low dimensional views of the relationships between two sets of variables. These views, in the form of biplots, display familiar statistics: correlations between pairs of variables, and regression coefficients. (SLD)

Montreal college students (n=457) rated 21 life domains (for example, education, friends, leisure, health) in terms of degree of importance, frequency of involvement, and level of impact. The list of domains significantly related to life satisfaction proved to be much broader for females than for males. (DM)

Discusses three topics related to interpretation of discriminant analyses (DA's): (1) partial F ratios and partial Wilks's lambdas for predictor variables in standard, step-down, and stepwise DA's; (2) relation of goals of classification to definition/evaluation of classification rules; and (3) significance tests for total hit rates in internal…

Homogeneity analysis (multiple correspondence analysis), which is usually applied to "k" separate variables, was applied to sets of variables by using sums within sets. The resulting technique, OVERALS, uses optimal scaling. The corresponding OVERALS computer program minimizes a least squares loss function via an alternating least…

A new method, based on loglinear models, is proposed for statistical analysis of dyadic social interaction data measured over time. The data are assumed to be realizations of a social network of a fixed set of actors interacting on a single relation. Associative and predictive statistical models are developed. (TJH)

Standardization procedures in discriminant analysis are discussed. Three leading software packages--SPSSX, BMDP, and SAS--are compared in terms of their calculations of unstandardized and standardized discriminant coefficients. Estimation procedures are described for each. Arguments are presented for within-group, rather than total, variance…