Response data containing an excessive number of zeros are referred to as zero-inflated data. When differential item functioning (DIF) detection is of interest, zero-inflation can attenuate DIF effects in the total sample and lead to underdetection of DIF items. The current study presents a DIF detection procedure for response data with excess…

Partial correlation coefficients are often used as effect sizes in the meta-analysis and systematic review of multiple regression analysis research results. There are two well-known formulas for the variance and thereby for the standard error (SE) of partial correlation coefficients (PCC). One is considered the "correct" variance in the…

Forensic science practitioners compare visual evidence samples (e.g. fingerprints) and decide if they originate from the same person or different people (i.e. fingerprint 'matching'). These tasks are perceptually and cognitively complex--even practising professionals can make errors--and what limited research exists suggests that existing…

This study compared the quality of survey data collected from Mechanical Turk (MTurk) workers and college students. Three groups of participants completed the same survey. "MTurk" respondents completed the survey as paid workers using the Mechanical Turk crowdsourcing platform. "Student Online" respondents also completed the…

This dissertation developed a new learner corpus of Japanese and introduced an error and linguistic annotation scheme specifically designed for Japanese particles. The corpus contains texts written by learners who are in the first year to fourth year university level Japanese courses. The texts in the corpus were tagged with part-of-speech and…

Temporality-driven covariate classification had limited impact on: the specification of directed acyclic graphs (DAGs) by 85 novice analysts (medical undergraduates); or the risk of bias in DAG-informed multivariable models designed to generate causal inference from observational data. Only 71 students (83.5%) managed to complete the…

When an assessment undergoes changes to the administration or instrument, bridge studies are typically used to try to ensure comparability of scores before and after the change. Among the most common and powerful is the common population linking design, with the use of a linear transformation to link scores to the metric of the original…

Purpose: Polysyllables, words of 3 or more syllables, represent almost 30% of words used in American English. The purpose of this tutorial is to support speech-language pathologists' (SLPs') assessment and analysis of polysyllables, extending the focus of published assessment tools that focus on sampling and analyzing children's segmental accuracy…

De la Torre and Deng suggested a resampling-based approach for person-fit assessment (PFA). The approach involves the use of the [math equation unavailable] statistic, a corrected expected a posteriori estimate of the examinee ability, and the Monte Carlo (MC) resampling method. The Type I error rate of the approach was closer to the nominal level…

This study investigates the psychological effect of a wrong question with wrong items on answering to the next question in a test of structure. Forty students selected through stratified random sampling are given 15 questions of a standardized test namely a TOEFL structure test in which questions number 7 and number 11 are wrong and their answers…

A large number of approaches have been proposed for estimating and testing the significance of indirect effects in mediation models. In this study, four sets of Monte Carlo simulations involving full latent variable structural equation models were run in order to contrast the effectiveness of the currently popular bias-corrected bootstrapping…

Raju, van der Linden, and Fleer (1995) introduced a framework for differential functioning of items and tests (DFIT) for unidimensional dichotomous models. Since then, DFIT has been shown to be a quite versatile framework as it can handle polytomous as well as multidimensional models both at the item and test levels. However, DFIT is still limited…

It is more common for educational and psychological data to be nonnormal than to be approximately normal. This tendency may lead to bias and error in point estimates of the Pearson correlation coefficient. In a series of Monte Carlo simulations, the Pearson correlation was examined under conditions of normal and nonnormal data, and it was compared…

This paper presents the Agresti & Coull "Adjusted Wald" method for computing confidence intervals and margins of error for common proportion estimates. The presented method is easily implementable by business students and practitioners and provides more accurate estimates of proportions particularly in extreme samples and small…

Purpose: Early apraxia of speech (AOS) research has characterized errors as being variable, resulting in a number of different error types being produced on repeated productions of the same stimuli. Conversely, recent research has uncovered greater consistency in errors, but there are limited data examining sound errors over time (more than one…