Using the Criterion-Predictor Factor Model to Compute the Probability of Detecting Prediction Bias with Ordinary Least Squares Regression

The study of prediction bias is important and the last five decades include research studies that examined whether test scores differentially predict academic or employment performance. Previous studies used ordinary least squares (OLS) to assess whether groups differ in intercepts and slopes. This study shows that OLS yields inaccurate inferences for prediction bias hypotheses. This paper builds upon the criterion-predictor factor model by demonstrating the effect of selection, measurement error, and measurement bias on prediction bias studies that use OLS. The range restricted, criterion-predictor factor model is used to compute Type I error and power rates associated with using regression to assess prediction bias hypotheses. In short, OLS is not capable of testing hypotheses about group differences in latent intercepts and slopes. Additionally, a theorem is presented which shows that researchers should not employ hierarchical regression to assess intercept differences with selected samples.     

Ordinary Least Squares Estimation of Parameters in Exploratory Factor Analysis With Ordinal Data

Exploratory factor analysis (EFA) is often conducted with ordinal data (e.g., items with 5-point responses) in the social and behavioral sciences. These ordinal variables are often treated as if they were continuous in practice. An alternative strategy is to assume that a normally distributed continuous variable underlies each ordinal variable. The EFA model is specified for these underlying continuous variables rather than the observed ordinal variables. Although these underlying continuous variables are not observed directly, their correlations can be estimated from the ordinal variables. These correlations are referred to as polychoric correlations. This article is concerned with ordinary least squares (OLS) estimation of parameters in EFA with polychoric correlations. Standard errors and confidence intervals for rotated factor loadings and factor correlations are presented. OLS estimates and the associated standard error estimates and confidence intervals are illustrated using personality trait ratings from 228 college students. Statistical properties of the proposed procedure are explored using a Monte Carlo study. The empirical illustration and the Monte Carlo study showed that (a) OLS estimation of EFA is feasible with large models, (b) point estimates of rotated factor loadings are unbiased, (c) point estimates of factor correlations are slightly negatively biased with small samples, and (d) standard error estimates and confidence intervals perform satisfactorily at moderately large samples.     

Match Madness: Probability Matching in Prediction of the NCAA Basketball Tournament1

Every year, billions of dollars are spent gambling on the outcomes of the NCAA men's basketball tournament. This study examines how individuals make predictions for tournament pools, one of the most popular forms of betting, in which individuals must correctly predict as many games in the tournament as possible. We demonstrate that individuals predict more upsets (i.e., wins by a higher seeded team) than would be considered rational by a normative choice model, and that individuals are no better than chance at doing so. These predictions fit a pattern of probability matching, in which individuals predict upsets at a rate equal to past frequency. This pattern emerges because individuals believe the outcomes of the games are nonrandom and, therefore, predictable.     

Using a System of Least Prompts Procedure to Teach Telephone Skills to Elementary Students with Cognitive Disabilities

Using the telephone to contact others can be an important skill in maintaining friendships with peers. This investigation used a system of least prompts (SLP) procedures to teach two telephone skills to 3 elementary students with cognitive disabilities: (a) placing phone calls and (b) leaving recorded voicemail messages. The SLP procedure was effective in teaching both skills to all 3 students. Results for maintenance and generalization, however, were mixed. This investigation was completed to partially satisfy the thesis requirement for a Master’s degree at the University of Kentucky.     

A Multi-informant Multi-Measure Approach to the Two Factor Model of Emotion with Youth

The two-factor model of emotion clarifies the complexities of the relationship between anxiety and depression through their varying associations with positive and negative affect. Although this model’s structure has been studied in children, the lack of parent report measures on model-specific constructs has thus far prevented a multi-informant perspective on the model. Capitalizing on recent advancements in parent report assessment instruments, the present investigation aimed to confirm the two-factor model of emotion per child self-report; expand the model’s applicability to include parent report; and create a combined-informant model with a large number of parent-child dyad pairs (N?=?610). Structural equation modeling demonstrated good fit within parent and child informant models, but diminished fit for the multi-informant model. These results suggest a high degree of robustness with respect to informant type. Implications for the integration of multi-informant assessment information are discussed.     

Recovering Substantive Factor Loadings in the Presence of Acquiescence Bias: A Comparison of Three Approaches

Researchers are often advised to write balanced scales (containing an equal number of positively and negatively worded items) when measuring psychological attributes. This practice is recommended to control for acquiescence bias (ACQ). However, little advice has been given on what to do with such data if the researcher subsequently wants to evaluate a 1-factor model for the scale. This article compares 3 approaches for dealing with the presence of ACQ bias, which make different assumptions: an ipsatization approach based on the work of Chan and Bentler (CB; 1993), a confirmatory factor analysis (CFA) approach that includes an ACQ factor with equal loadings (Billiet & McClendon, 2000; Mirowsky & Ross, 1991), and an exploratory factor analysis (EFA) approach with a target rotation (Ferrando, Lorenzo-Seva, & Chico, 2003). We also examine the “do nothing” approach which fits the 1-factor model to the data ignoring the presence of ACQ bias. Our main findings are that the CFA method performs best overall and that it is robust to the violation of its assumptions, the EFA and the CB approaches work well when their assumptions are strictly met, and the “do nothing” approach can be surprisingly robust when the ACQ factor is not very strong.     

Detecting Treatment Effects with Small Samples: The Power of Some Tests Under the Randomization Model

Randomization tests are often recommended when parametric assumptions may be violated because they require no distributional or random sampling assumptions in order to be valid. In addition to being exact, a randomization test may also be more powerful than its parametric counterpart. This was demonstrated in a simulation study which examined the conditional power of three nondirectional tests: the randomization t test, the Wilcoxon–Mann–Whitney (WMW) test, and the parametric t test. When the treatment effect was skewed, with degree of skewness correlated with the size of the effect, the randomization t test was systematically more powerful than the parametric t test. The relative power of the WMW test under the skewed treatment effect condition depended on the sample size ratio.     

Erratum to: Beyond the Mean: A Flexible Framework for Studying Causal Effects Using Linear Models

Psychometrika - The original version of the article contains the below listed errors.     

Erratum to: A Simple Method for Comparing Complex Models: Bayesian Model Comparison for Hierarchical Multinomial Processing Tree Models Using Warp-III Bridge Sampling

Psychometrika - The article A SIMPLE METHOD FOR COMPARING COMPLEX MODELS:     

Using a High Probability Command Sequence to Increase Classroom Compliance: The Role of Behavioral Momentum

One of the most problematic behaviors in children with developmental disabilities is noncompliance. Although behavioral research has provided strategies to impact noncompliance, oftentimes the methodologies are consequent techniques, which may not be conducive to implementation by the classroom teacher. In this teacher-designed and implemented study, a sequence of high-probability instructional commands preceded the targeted low-probability command, in an attempt to increase compliance to the low-probability command. Results, discussed within the body of behavioral momentum research, showed an increase in compliance to low-probability classroom commands for a seven year-old student with moderate mental retardation and Down Syndrome. Results are discussed as (a) an effective, antecedent approach to classroom compliance and (b) re-connecting the gap between applied behavioral research and experimentally controlled classroom practice.     

Predicting counterproductive work behaviors with sub-clinical psychopathy: Beyond the Five Factor Model of personality

Organizational psychologists examining personality’s relation to work behavior have focused largely on the “normal” traits comprising the Five Factor Model (FFM). However, given the aversive nature of sub-clinical psychopathy (e.g., callous affect, impulsivity), we posit that this toxic personality profile will enhance the prediction of negative work outcomes, namely forms of counterproductive workplace behavior (CWB). Study 1 (N = 193) examined the value of sub-clinical psychopathy and the FFM in predicting intentions to engage in CWB; results support prior research indicating that both agreeableness and conscientiousness significantly correlated with CWB. In addition, sub-clinical psychopathy predicted CWB above and beyond the FFM. Study 2 (N = 360) extended the findings of Study 1 by examining interpersonally deviant behavior in a team context. While agreeableness was significantly related to interpersonal deviance in Study 2, conscientiousness was not. Results from Study 2 replicate Study 1, suggesting that sub-clinical psychopathy accounted for the majority of the explained variance in interpersonal deviance. Overall, the results support the value of using sub-clinical psychopathy to predict CWB.