This article proposes an intuitive approach for predictive discriminant analysis with mixed continuous, dichotomous, and ordered categorical variables that are defined via an underlying multivariate normal distribution with a threshold specification. The classification rule is based on the comparison of the observed data logarithm probability…

In order to investigate unique and shared characteristics and to determine factors predictive of group classification, quantitative comparisons of behavioral and emotional problems were assessed using the Developmental Behavior Checklist (DBC-P) and the Vineland Adaptive Behavior Scales in autistic disorder, Williams syndrome (WS), and…

The reported study in this paper examined the continuing viability of Florida's 2+2 articulation agreement by comparing academic success and persistence among Florida public community college graduates (n = 1,738) and native (n = 874) juniors at three universities. Discriminant analysis yielded statistically significant differences. Transfer…

The purpose of this study was to identify factors distinguishing Mexican American women living near the U.S.-Mexican border who are resilient to the experience of stress from those who are not. The study sample consisted of 418 participants ranging in age from 20 to 61 years. Data were gathered through a self-report survey instrument composed of…

In multilingual Asian communities, determining language dominance for clinical assessment and intervention is often complex. The aim of this study was to develop a self-report classification tool for identifying the dominant language in English-Mandarin bilinguals. Participants (N = 168) completed a questionnaire on language history and…

After reviewing past efforts related to computer-based reading disability (RD) assessment, we present a fully automated screening battery that evaluates critical skills relevant for RD diagnosis designed for unsupervised application in the Greek educational system. Psychometric validation in 301 children, 8-10 years old (grades 3 and 4; including…

The purpose of this study was to explore factors that may affect string teachers' career decisions. Six hundred string teachers were mailed a questionnaire designed to elicit responses about multiple factors and projected career plans in 1 year and in 5 years, and 304 teachers responded. The majority of teachers planned to remain in their…

Among 261 undergraduate women, increased severity of eating disorders along a continuum was associated with decreased self-esteem, increased perfectionism, and increased scores on 7 subscales of the Eating Disorders Inventory-2. Women with eating disorders differed from both symptomatic women and asymptomatic women on all variables, whereas…

An empirical comparison of three proposed indices of predictor variable potency is presented. These indices are: (1) the scaled weights of the first Fisher-type discriminant function, (2) the total group estimates of the correlations between each predictor variable and the first Fisher-type function, and (3) the within-groups estimates of the…

The purpose of this study was to determine which of six methods of ordering variables in a discriminant analysis yields subsets of variables that have the greatest discriminatory power. One method is based on univariate mean-square (or F) ratios, a second method on stepwise ordering, two methods on linear discriminant function (LDF) variable…

The stabilities of standardized (ß) and structure (rs) coefficients in canonical (CA) and discriminant analyses (DA) were studied. Four different situations were studied--two pertaining to CA and two to DA. The situations were meant to represent "somewhat typical" and yet varying research conditions that often would not be thought to be…

Two data sets are cluster-analyzed by the minimum variance procedure, and centroid vectors for the first are calculated. The objects of the second are assigned to the nearest centroid calculated in the first data set, and the results are evaluated in terms of stability and accuracy. (Author/BW)

Discussion of natural language processing focuses on experiments using linear discriminant analysis to distinguish "Wall Street Journal" texts from "Federal Register" tests using information about the frequency of occurrence of word boundaries, sentence boundaries, and punctuation marks. Displays and interprets results in terms…