Showing 1 - 4 of 4 Research Library Publications

Extracting Linguistic Signal From Item Text and Its Application to Modeling Item Characteristics

Posted: | Victoria Yaneva, Peter Baldwin, Le An Ha, Christopher Runyon

Advancing Natural Language Processing in Educational Assessment: Pages 167-182

 

This chapter discusses the evolution of natural language processing (NLP) approaches to text representation and how different ways of representing text can be utilized for a relatively understudied task in educational assessment – that of predicting item characteristics from item text.

Category:Assessment-Oriented Research, Applications of Technology, Scoring

Assessment of Clinical Skills: A Case Study in Constructing an NLP-based Scoring System for Patient Notes

Posted: | Polina Harik, Janet Mee, Christopher Runyon, Brian E. Clauser

Advancing Natural Language Processing in Educational Assessment: Pages 58-73

 

This chapter describes INCITE, an NLP-based system for scoring free-text responses. It emphasizes the importance of context and the system’s intended use and explains how each component of the system contributed to its accuracy.

Category:Assessment-Oriented Research, Applications of Technology, Scoring

Correlations Between the USMLE Step Examinations, American College of Physicians In-Training Examination, and ABIM Internal Medicine Certification Examination

Posted: | F.S. McDonald, D. Jurich, L.M. Duhigg, M. Paniagua, D. Chick, M. Wells, A. Williams, P. Alguire

Academic Medicine: September 2020 - Volume 95 - Issue 9 - p 1388-1395

 

This article aims to assess the correlations between United States Medical Licensing Examination (USMLE) performance, American College of Physicians Internal Medicine In-Training Examination (IM-ITE) performance, American Board of Internal Medicine Internal Medicine Certification Exam (IM-CE) performance, and other medical knowledge and demographic variables.

Category:Assessment-Oriented Research, Scoring, Links to Outcomes, Product-Oriented Research, USMLE

A Comparison of Strategies for Smoothing Parameter Selection for Mixed-Format Tests Under the Random Groups Design

Posted: | C. Liu, M. J. Kolen

Journal of Educational Measurement: Volume 55, Issue 4, Pages 564-581

 

Smoothing techniques are designed to improve the accuracy of equating functions. The main purpose of this study is to compare seven model selection strategies for choosing the smoothing parameter (C) for polynomial loglinear presmoothing and one procedure for model selection in cubic spline postsmoothing for mixed‐format pseudo tests under the random groups design.

Category:Assessment-Oriented Research, Reliability/Validity, Scoring