A two-level data set can be structured in either long format (LF) or wide format (WF), and both have corresponding SEM approaches for estimating multilevel models. Intuitively, one might expect these approaches to perform similarly. However, the two data formats yield data matrices with different numbers of columns and rows, and their "cols :…

The design of research studies utilizing binary multilevel models must necessarily incorporate knowledge of multiple factors, including estimation method, variance component size, or number of predictors, in addition to sample sizes. This Monte Carlo study examined the performance of random effect binary outcome multilevel models under varying…

There are usually limited user evaluation of resources on a recommender system, which caused an extremely sparse user rating matrix, and this greatly reduce the accuracy of personalized recommendation, especially for new users or new items. This paper presents a recommendation method based on rating prediction using causal association rules.…

In light of the emergence of statistical analysis techniques based on data mining in education sciences, and the potential they offer to detect non-trivial information in large databases, this paper presents a procedure used to detect factors linked to academic achievement in large-scale assessments. The study is based on a non-experimental,…

A general program for item-response analysis is described that uses the stabilized Newton-Raphson algorithm. This program is written to be compliant with Fortran 2003 standards and is sufficiently general to handle independent variables, multidimensional ability parameters, and matrix sampling. The ability variables may be either polytomous or…

This study investigated personality correlates of early adolescents' tendency to either defend victims of bullying or to avoid involvement in bullying situations. Participants were 591 Dutch fifth- and sixth-grade students (X-bar[subscript age] = 11.42 years). Hierarchical regression models were run to predict these students' peer-reported…

Indefinite symmetric matrices that are estimates of positive-definite population matrices occur in a variety of contexts such as correlation matrices computed from pairwise present missing data and multinormal based methods for discretized variables. This note describes a methodology for scaling selected off-diagonal rows and columns of such a…

A theorem of Spjotvoll (1972) was used to determine and apply a confidence interval for the difference of two multiple correlations based on observations from a single sample. Spjotvoll's method of comparing regression functions is also applicable to a comparison of dependent multiple correlations, an unsolved problem posed by Hotelling in 1940.…

This paper discusses how full model dummy variables can be used with partial correlation or multiple regression procedures to compute matrices of pooled within-group correlations. (Author/CTM)

A stepwise canonical procedure, including two selection indices for variable deletion and a rule for stopping the iterative procedure, was derived as a method of selecting core variables from predictors and criteria. The procedure was applied to simulated data varying in the degree of built in structures in population correlation matrices, number…

The purpose of this paper is to demonstrate the use of the general linear model (GLM) in problems with repeated measures on a dependent variable. Such problems include pretest-posttest designs, multitrial designs, and groups by trials designs. For each of these designs, a GLM analysis is demonstrated wherein full models are formed and restrictions…

New ways of using factor analysis in research designs are suggested in this paper that would allow research to move in new directions that are being suggested for educational technology. A brief simplified overview of factor-analytic techniques is given, followed by a description of some recent developments in factor-analytic techniques which make…

The optimum weighting of variables to predict a dependent-criterion variable is an important problem in nearly all of the social and natural sciences. Although the predominant method, multiple regression analysis (MR), yields optimum weights for the sample at hand, these weights are not generally optimum in the population from which the sample was…

The results of an algorithm which is designed to take a set of commonality coefficients, either real or manipulated, and, if possible, produce one or more sets of regressor correlations that are consistent with them are examined. A number of different ways of resolving the higher order commonality values into their lower orders were tried and the…

A linear classification rule (used with equal covariance matrices) was contrasted with a quadratic rule (used with unequal covariance matrices) for accuracy of internal and external classification. The comparisons were made for seven situations which resulted from combining three data conditions (equal and unequal covariance matrices, minimal and…