In this simulation study, we investigate the power and Type I error rate of a procedure based on the mean and covariance structure analysis (MACS) model in detecting differential item functioning (DIF) of graded response items with five response categories. The following factors were manipulated: type of DIF (uniform and non-uniform), DIF…

Structural equation modeling allows several methods of estimating the disattenuated association between 2 or more latent variables (i.e., the measurement model). In one common approach, measurement models are specified using item parcels as indicators of latent constructs. Item parcels versus original items are often used as indicators in these…

Learning is an important aspect of aging productively. This paper describes results from 2645 respondents (aged from 50 to 74+ years) to a 165-variable postal survey in Australia. The focus is on learning and its relation to work; social, spiritual, and emotional status; health; vision; home; life events; and demographic details. Clustering…

Using the cluster generation procedure proposed by D. Steinley and R. Henson (2005), the author investigated the performance of K-means clustering under the following scenarios: (a) different probabilities of cluster overlap; (b) different types of cluster overlap; (c) varying samples sizes, clusters, and dimensions; (d) different multivariate…

This study focuses on comparing the creative thinking and reasoning abilities of deaf and hearing children. Two groups of deaf (N = 210) and hearing children (N = 200) were chosen based on specific criteria. Two instruments were used in the study: the Torrance Tests of Creative Thinking-Figural, Form A and Matrix Analogies Test. Canonical…

The use of repeated measures research designs is explored. Repeated measures designs are often advantageous and can be implemented in a variety of research settings. One of the main advantages in repeated measures designs is the control of subject variability. Other advantages are the reduction of error variance and economy in subject recruitment.…

Research in the area of multivariate outliers is reviewed, emphasizing the problems associated with definition and identification. Treatment of the problem can be traced to 1777 and the work of D. Bernoulli. Most of the many procedures developed for identifying outliers proceed sequentially starting with the most aberrant observation, or proceed…

A simulation study was conducted to identify the best hot-deck variation to impute missing values. The three variations included in the study were the hot-deck random, the hot-deck sequential, and the hot-deck distance. The properties of these methods were investigated under three levels of the proportion of incomplete records and four levels…

The use of multivariate statistics in behavioral research is investigated, with emphasis on the reasons why multivariate methods can be so important. The concepts of testwise and experimentwise error are explained, and it is noted that multivariate methods can be used to control the inflation of experimentwise Type I error. It is also noted that…

This note described a FORTRAN IV, CDC, computer program for the canonical analysis of a two-way contingency table. (Author)

A component method is presented for maximizing estimates of a statistical procedure called redundancy analysis. Relationships of redundancy analysis to multiple correlation and principal component analysis are pointed out. An elaborate example comparing canonical correlation analysis and redundancy analysis on artificial data is presented.…

Explains factor analysis, discussing its relation to other multivariate techniques and describing characteristics of the data to consider in determining the appropriateness of factor analysis. Reviews considerations in making decisions about communality estimates, factor extraction, the number of factors to rotate, methods of factor rotation,…

Computer sampling from a multivariate normal spherical population was used to evaluate Type I error rates for a test of P = I based on Fisher's tanh(sup minus 1) variance stabilizing transformation of the correlation coefficient. (Author/TJH)

Fleiss' popular multirater kappa is known to be influenced by prevalence and bias, which can lead to the paradox of high agreement but low kappa. It also assumes that raters are restricted in how they can distribute cases across categories, which is not a typical feature of many agreement studies. In this article, a free-marginal, multirater…