Explores effects of ignoring one or more levels of variation in hierarchical linear regression analysis, using a model with four hierarchical levels. Ignoring the top or intermediate levels influences fixed coefficients, variance components, and their corresponding standard error and can lead to different research conclusions. (Contains 16…

Explores race, class, educational level, and parental perceptions as they affect parental participation in schools, analyzing data generated by a 1991 National Commission on Children survey. Discovered clear interactions and correlations among all variables and respondents' participation in various school activities. Suggests a prediction model…

Analyzes overall effectiveness and efficiency of Chicago public elementary schools, evaluating performance changes following fundamental school reforms of 1988-89. Some schools are effective regarding student achievement at certain points in time; others are efficient in adding value (improving disadvantaged students' performance). Some have both…

Utilizes principal-component regression analysis to examine the relative contributions of 11 ranking criteria used to construct a periodical's tier rankings of national universities. Although "U.S. News & World Report" assigns the greatest weight to academic reputation, enrolled students' average SAT scores constitute the most…

Studies 248 adolescents who had been in a Serious Offender Program to examine the relative predictiveness of: a common risk assessment tool; a battery of psychological tests; and a combination of demographic and theoretical factors. Regression procedures indicate that the following are significant predictors: prior commitment; male; gang members;…

A statistical power algorithm based on the Fisher Z method is developed for cutoff-based random clinical trials and the single cutoff-point (regression-discontinuity) design that has no randomization. This article quantifies power and sample size estimates for various levels of power and cutoff-based assignment. (Author/SLD)

A strategy is proposed for conceptualizing moderating relationships based on their type (strictly correlational and classically correlational) and form, whether continuous, noncontinuous, logistic, or quantum. Results of computer simulations comparing three statistical approaches for assessing moderator variables are presented, and advantages of…

Describes a study of undergraduates that examined the effects of the cognitive load associated with using hypertext linking capabilities in instructional materials. Highlights include cognitive flexibility theory; hypertext navigation; results of criterion measures and regression analysis; and cognitive load theory. (Contains 56 references.) (LRW)

Applied the technique of artificial neural networks to predict which students were likely to apply to one research university. Compared the results to the traditional analysis tool, logistic regression modeling. Found that the addition of artificial intelligence models was a useful new tool for predicting student application behavior. (EV)

Eight variations of a general matching design, matching program participants and a control group, were studied through simulation, for their effectiveness in evaluating programs for the gifted and talented. A regression-discontinuity design provided the best approach, with unbiased estimates of program effects. (SLD)

Compared differential item functioning detection rates for logistic regression and analysis of variance for dichotomously scored items using simulated data and varying test length, sample size, discrimination rate, and underlying ability. Explains why the logistic regression method is recommended for most applications. (SLD)

Applied the capture-recapture model, through a Poisson regression to a time series of data for admissions to treatment from 1987 to 1996 to estimate the number of heroin addicts in Texas who are "at-risk" for treatment. The entire data set produced estimates that were lower and more plausible than those produced by drawing samples,…

The present study investigated the factor structure and item analysis of the Mini Asthma Quality of Life Questionnaire (MiniAQLQ) in a sample of 258 community-dwelling asthmatic adults between the ages of 16 and 87 years. The mean age was 56 years for males (N = 99) and 50 years for females (N = 159). This study compared the fit of three factor…

This is the fourth in a series of studies whose purpose has been to develop a theoretical model of selected extramusical variables' ability to explain solo and small-ensemble festival ratings. Authors of the second and third of these (Bergee & McWhirter, 2005; Bergee & Westfall, 2005) used logistic regression as the basis for their…

Using American Citizen Participation Survey data (Verba et al. 1995a), we perform logistic regression analyses to adjudicate between three core explanations for individual protest: biographical availability, political engagement and structural availability. We calculate estimated probabilities to weigh the relative effects of these factors on the…