Premium
Demonstrating Construct Validity of the American Board of Physical Medicine and Rehabilitation Part I Examination: An Analysis of Dimensionality
Author(s) -
Raddatz Mikaela M.,
Robinson Lawrence R.
Publication year - 2017
Publication title -
pmandr
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.617
H-Index - 66
eISSN - 1934-1563
pISSN - 1934-1482
DOI - 10.1016/j.pmrj.2017.02.003
Subject(s) - construct validity , united states medical licensing examination , item response theory , rasch model , construct (python library) , psychometrics , certification , empirical examination , dimension (graph theory) , local independence , psychology , medicine , clinical psychology , computer science , mathematics , medical education , developmental psychology , actuarial science , medical school , pure mathematics , political science , law , business , programming language
Background Ideally, high‐stakes examinations assess 1 dimension of medical knowledge to produce precise estimates of a candidate's performance. It has not been reported whether the American Board of Physical Medicine and Rehabilitation Part 1 Certification Examination (ABPMR‐CE‐1) is unidimensional or not. Objective To examine the ABPMR‐CE‐1 to measure how many dimensions it assesses. Design Retrospective observational study. Setting We assessed examination results from the 2015 ABPMR‐CE‐1. Participants A total of 489 deidentified candidates taking the 2015 ABPMR‐CE‐1. Methods A 1‐parameter Item Response Theory (IRT) measurement model was utilized. A Principal Components Analysis (PCA) of standardized residual correlations was used to detect multidimensionality. Main Outcome Measure Number of primary dimensions reflected in the 325 test questions. Results The results of the dimensionality analysis indicated that the ABPMR‐CE‐1 examination is highly unidimensional from a psychometric perspective. Expert content review of the substantive content of small contrasting clusters of questions provided additional assurance of the unidimensional nature of the examination. Conclusions The ABPMR‐CE‐1 appears indeed to measure a single construct, which suggests a sound structure of the examination. It closely approximates the assumption of statistical unidimensionality. Level of Evidence Not applicable.