The purpose of this study is to describe and evaluate a multilingual automated essay scoring (AES) system for grading essays in three languages. Two different sentence embedding models were evaluated within the AES system, multilingual BERT (mBERT) and language-agnostic BERT sentence embedding (LaBSE). German, Italian, and Czech essays were…

Objective: ADHD and autism are complex and frequently co-occurring neurodevelopmental conditions with shared etiological and pathophysiological elements. In this paper, we attempt to differentiate these conditions among the young people in terms of intrinsic patterns of brain connectivity revealed during resting state using machine learning…

This dissertation describes an experiment to investigate how learners with different levels of background in computer science learn core concepts of computer science, in particular, algorithms. We designed a study to focus on cognitive task analysis for eliciting the empirical mental elements of learning two graph algorithms. Cognitive workload…

Considerable debate continues regarding the efficacy of the website RateMyProfessors.com (RMP). To date, however, virtually no direct, experimental research has been reported which directly bears on questions relating to sampling adequacy or item adequacy in producing what favorable correlations have been reported. The authors compare the data…

Many colleges and university's use SAT math scores or math placement tests to place students in the appropriate math course. This study compares the use of math placement scores and SAT scores for 188 freshman students. The student's grades and faculty observations were analyzed to determine if the SAT scores and/or college math assessment scores…

Two quasi-experimental field studies were conducted to evaluate the psychometric equivalence of computerized and paper-and-pencil job satisfaction measures. The present research extends previous work in the area by providing better control of common threats to validity in quasi-experimental research on test mode effects and by evaluating a more…

This article explores the effect on assessment of "translating" paper and pencil test items into their computer equivalents. Computer versions of a set of mathematics questions derived from the paper-based end of key stage 2 and 3 assessments in England were administered to age appropriate pupil samples, and the outcomes compared.…

Twelve structural models of similarity were fitted to data from conventional and computer adaptive test (CAT) batteries measuring the same aptitude in a double cross-validation design. Three of the 12 models, including a multiplicative structure model, performed well, providing support for using CATs as replacements for conventional tests. (NSF)

Using a within-subjects design, computer-based and paper-based tests of aircraft silhouette recognition were administered to 83 male naval pilots and flight officers to determine the relative reliabilities and validities of 2 measurement modes. Relative reliabilities and validities of the two modes were contingent on the multivariate measurement…

A developed computer-administered form of the Hamilton Anxiety Scale and the clinician form of the instrument were administered to 214 psychiatric outpatients and 78 community adults. Results support the reliability and validity of the computer-administered version as an alternative to the clinician-administered version. (SLD)

Computer simulations were run to measure the relationship between testlet validity and factors of item pool size and testlet length for both adaptive and linearly constructed testlets. Making a testlet adaptive yields only modest increases in aggregate validity because of the peakedness of the typical proficiency distribution. (Author/SLD)

Laird studies the relationship between two computerized nursing tests and finds a relationship between the two sets of scores. (Contains 2 tables.)

Three descriptive statistics (difficulty, discrimination, and reliability) of multiple-choice (MC) test items were compared to those of a new (1980s) format of machine-scored questions. The new method, answer-bank multi-digit testing (MDT), uses alphabetized lists of up to 1,000 alternatives and approximates the completion style of assessment…

To investigate the psychometric feasibility of replacing a paper-and-pencil licensing examination with a computer-administered test, a validity study was conducted. The computer-administered test (Cadm) was a common set of items for all test takers, distinct from computerized adaptive testing, in which test takers receive items appropriate to…

A study was conducted to validate the Army's Computerized Adaptive Screening Test (CAST), using data from 2,240 applicants from 60 army recruiting stations across the nation. CAST is a computer-assisted adaptive test used to predict performance on the Armed Forces Qualification Test (AFQT). AFQT scores are computed by adding four subtest scores of…