A study tested the notion that information stories in "USA Today" are more readable because its editors shorten them by leaving out background details. It also examined whether readers comprehend as much from stories written in "USA Today" style as they do from stories written in the more traditional "New York Times"…

This paper empirically and systematically assessed the performance of bootstrap resampling procedure as it was applied to a regression model. Parameter estimates from Monte Carlo experiments (repeated sampling from population) and bootstrap experiments (repeated resampling from one original bootstrap sample) were generated and compared. Sample…

It is recognized that parametric methods (e.g., t-tests, discriminant analysis, and methods based on analysis of variance) are special cases of canonical correlation analysis. In canonical correlation it has been argued that structure coefficients must be computed to correctly interpret results. It follows that structure coefficients may be useful…

Langmuir's model is studied for the situation where epsilon is independently and identically normally distributed. The "Y/x" versus "Y" plot had a 90% mid-range that did not contain the true curve in a vast portion of the range of "x". The "1/Y" versus "1/chi" plot had undefined expected values,…

This publication provides results of a longitudinal study of young firms and their owners. Data represent the responses of a national sample of new business owners (N=2,994) who were members of the National Federation of Independent Business in May 1985 and had been in business for no more than 17 months with the average respondent owning the…

This paper explains how commonality analysis (CA) can be conducted using a specific Statistical Analysis System (SAS) procedure and some simple computations. CA is used in educational and social science research to partition the variance of a dependent variable into its constituent predicted parts. CA determines the proportion of explained…

This paper examines some of the problems that arise when conducting multivariate analyses with incomplete data. The literature on the effectiveness of several missing data procedures (MDP) is summarized. The most widely used MDPs are: (1) listwise deletion; (2) pairwise deletion; (3) variable mean; (4) correlational methods. No MDP should be used…

Using a longitudinal data set obtained from 169 pre-adolescent children between the ages of 8 and 13 years, this study statistically divided locus of control into two independent components. The first component was noted as "age-dependent" (AD) and was determined by predicted values generated by regressing children's ages onto their…

Now that the school effectiveness field is maturing, more refined and contextually sensitive observations about schools are possible. This paper focuses on socioeconomic status (SES) as one social context variable demonstrating substantial predictive power in numerous school improvement studies. Instead of viewing middle class behavior as superior…

The MacArthur/Spencer special project on Illinois school finance is dedicated to the exploration of three central concepts in Illinois school finance: equity, adequacy, and efficiency. While most reports on the project have dealt directly with equity and adequacy, this report confronts the issue of efficiency by discussing the policy and legal…

Predictive discriminant analysis involves a technique used in multivariate classification, i.e., in predicting membership in well-defined groups for units on which multiple measures are available. The validation (assessment) of group membership predictions pertains to two problems: estimating true proportions of correct classifications (i.e., hit…

The findings and conclusions from research on predictive validity among markedly different groups are discussed. Empirical findings using the regression line neither support nor contradict the existence of bias or the hypothesis of differential validity. Conclusions drawn from the research are questionable. Elimination of bias in a test, contrary…

A two-stage generalized least squares model is developed for estimating the linear regression of an individual outcome on a group characteristic in studies of multilevel data. Results of this model are compared to the results of analytic methods, and formulas are developed for assessing the accuracy of the traditional approaches. (Author/JAZ)

Defines structural equation modeling (SEM) and points out its relation to other more familiar data-analytic techniques, as well as some of the potentials and pitfalls of SEM in the analysis of developmental data. Discussion focuses on causal modeling, path diagrams, ordinary least-squares regression analysis, and powerful methods for model…

Describes the strengths and weaknesses of a new type of multivariate technique, covariance structure analysis (LISREL). Provides a detailed example which shows how the use of covariance structure analysis can improve research sophistication and theory development in counseling psychology. (Author/ABB)