@article {173, title = {Replenishing a computerized adaptive test of patient-reported daily activity functioning}, journal = {Quality of Life Research}, volume = {18}, number = {4}, year = {2009}, note = {Haley, Stephen MNi, PengshengJette, Alan MTao, WeiMoed, RichardMeyers, DougLudlow, Larry HK02 HD45354-01/HD/NICHD NIH HHS/United StatesResearch Support, N.I.H., ExtramuralNetherlandsQuality of life research : an international journal of quality of life aspects of treatment, care and rehabilitationQual Life Res. 2009 May;18(4):461-71. Epub 2009 Mar 14.}, month = {May}, pages = {461-71}, edition = {2009/03/17}, abstract = {PURPOSE: Computerized adaptive testing (CAT) item banks may need to be updated, but before new items can be added, they must be linked to the previous CAT. The purpose of this study was to evaluate 41 pretest items prior to including them into an operational CAT. METHODS: We recruited 6,882 patients with spine, lower extremity, upper extremity, and nonorthopedic impairments who received outpatient rehabilitation in one of 147 clinics across 13 states of the USA. Forty-one new Daily Activity (DA) items were administered along with the Activity Measure for Post-Acute Care Daily Activity CAT (DA-CAT-1) in five separate waves. We compared the scoring consistency with the full item bank, test information function (TIF), person standard errors (SEs), and content range of the DA-CAT-1 to the new CAT (DA-CAT-2) with the pretest items by real data simulations. RESULTS: We retained 29 of the 41 pretest items. Scores from the DA-CAT-2 were more consistent (ICC = 0.90 versus 0.96) than DA-CAT-1 when compared with the full item bank. TIF and person SEs were improved for persons with higher levels of DA functioning, and ceiling effects were reduced from 16.1\% to 6.1\%. CONCLUSIONS: Item response theory and online calibration methods were valuable in improving the DA-CAT.}, keywords = {*Activities of Daily Living, *Disability Evaluation, *Questionnaires, *User-Computer Interface, Adult, Aged, Cohort Studies, Computer-Assisted Instruction, Female, Humans, Male, Middle Aged, Outcome Assessment (Health Care)/*methods}, isbn = {0962-9343 (Print)0962-9343 (Linking)}, author = {Haley, S. M. and Ni, P. and Jette, A. M. and Tao, W. and Moed, R. and Meyers, D. and Ludlow, L. H.} } @article {241, title = {Binary items and beyond: a simulation of computer adaptive testing using the Rasch partial credit model}, journal = {Journal of Applied Measurement}, volume = {9}, number = {1}, year = {2008}, note = {Lange, RenseUnited StatesJournal of applied measurementJ Appl Meas. 2008;9(1):81-104.}, pages = {81-104}, edition = {2008/01/09}, abstract = {Past research on Computer Adaptive Testing (CAT) has focused almost exclusively on the use of binary items and minimizing the number of items to be administrated. To address this situation, extensive computer simulations were performed using partial credit items with two, three, four, and five response categories. Other variables manipulated include the number of available items, the number of respondents used to calibrate the items, and various manipulations of respondents{\textquoteright} true locations. Three item selection strategies were used, and the theoretically optimal Maximum Information method was compared to random item selection and Bayesian Maximum Falsification approaches. The Rasch partial credit model proved to be quite robust to various imperfections, and systematic distortions did occur mainly in the absence of sufficient numbers of items located near the trait or performance levels of interest. The findings further indicate that having small numbers of items is more problematic in practice than having small numbers of respondents to calibrate these items. Most importantly, increasing the number of response categories consistently improved CAT{\textquoteright}s efficiency as well as the general quality of the results. In fact, increasing the number of response categories proved to have a greater positive impact than did the choice of item selection method, as the Maximum Information approach performed only slightly better than the Maximum Falsification approach. Accordingly, issues related to the efficiency of item selection methods are far less important than is commonly suggested in the literature. However, being based on computer simulations only, the preceding presumes that actual respondents behave according to the Rasch model. CAT research could thus benefit from empirical studies aimed at determining whether, and if so, how, selection strategies impact performance.}, keywords = {*Data Interpretation, Statistical, *User-Computer Interface, Educational Measurement/*statistics \& numerical data, Humans, Illinois, Models, Statistical}, isbn = {1529-7713 (Print)1529-7713 (Linking)}, author = {Lange, R.} } @article {273, title = {Combining computer adaptive testing technology with cognitively diagnostic assessment}, journal = {Behavioral Research Methods }, volume = {40}, number = {3}, year = {2008}, note = {McGlohen, MeghanChang, Hua-HuaUnited StatesBehavior research methodsBehav Res Methods. 2008 Aug;40(3):808-21.}, month = {Aug}, pages = {808-21}, edition = {2008/08/14}, abstract = {A major advantage of computerized adaptive testing (CAT) is that it allows the test to home in on an examinee{\textquoteright}s ability level in an interactive manner. The aim of the new area of cognitive diagnosis is to provide information about specific content areas in which an examinee needs help. The goal of this study was to combine the benefit of specific feedback from cognitively diagnostic assessment with the advantages of CAT. In this study, three approaches to combining these were investigated: (1) item selection based on the traditional ability level estimate (theta), (2) item selection based on the attribute mastery feedback provided by cognitively diagnostic assessment (alpha), and (3) item selection based on both the traditional ability level estimate (theta) and the attribute mastery feedback provided by cognitively diagnostic assessment (alpha). The results from these three approaches were compared for theta estimation accuracy, attribute mastery estimation accuracy, and item exposure control. The theta- and alpha-based condition outperformed the alpha-based condition regarding theta estimation, attribute mastery pattern estimation, and item exposure control. Both the theta-based condition and the theta- and alpha-based condition performed similarly with regard to theta estimation, attribute mastery estimation, and item exposure control, but the theta- and alpha-based condition has an additional advantage in that it uses the shadow test method, which allows the administrator to incorporate additional constraints in the item selection process, such as content balancing, item type constraints, and so forth, and also to select items on the basis of both the current theta and alpha estimates, which can be built on top of existing 3PL testing programs.}, keywords = {*Cognition, *Computers, *Models, Statistical, *User-Computer Interface, Diagnosis, Computer-Assisted/*instrumentation, Humans}, isbn = {1554-351X (Print)}, author = {McGlohen, M. and Chang, Hua-Hua} } @article {150, title = {Computer adaptive testing}, journal = {Journal of Applied Measurement}, volume = {6}, number = {1}, year = {2005}, note = {Gershon, Richard CReviewUnited StatesJournal of applied measurementJ Appl Meas. 2005;6(1):109-27.}, pages = {109-27}, edition = {2005/02/11}, abstract = {The creation of item response theory (IRT) and Rasch models, inexpensive accessibility to high speed desktop computers, and the growth of the Internet, has led to the creation and growth of computerized adaptive testing or CAT. This form of assessment is applicable for both high stakes tests such as certification or licensure exams, as well as health related quality of life surveys. This article discusses the historical background of CAT including its many advantages over conventional (typically paper and pencil) alternatives. The process of CAT is then described including descriptions of the specific differences of using CAT based upon 1-, 2- and 3-parameter IRT and various Rasch models. Numerous specific topics describing CAT in practice are described including: initial item selection, content balancing, test difficulty, test length and stopping rules. The article concludes with the author{\textquoteright}s reflections regarding the future of CAT.}, keywords = {*Internet, *Models, Statistical, *User-Computer Interface, Certification, Health Surveys, Humans, Licensure, Microcomputers, Quality of Life}, isbn = {1529-7713 (Print)}, author = {Gershon, R. C.} } @article {8, title = {Computer adaptive testing: a strategy for monitoring stroke rehabilitation across settings}, journal = {Stroke Rehabilitation}, volume = {11}, number = {2}, year = {2004}, note = {Andres, Patricia LBlack-Schaffer, Randie MNi, PengshengHaley, Stephen MR01 hd43568/hd/nichdEvaluation StudiesResearch Support, U.S. Gov{\textquoteright}t, Non-P.H.S.Research Support, U.S. Gov{\textquoteright}t, P.H.S.United StatesTopics in stroke rehabilitationTop Stroke Rehabil. 2004 Spring;11(2):33-9.}, month = {Spring}, pages = {33-39}, edition = {2004/05/01}, abstract = {Current functional assessment instruments in stroke rehabilitation are often setting-specific and lack precision, breadth, and/or feasibility. Computer adaptive testing (CAT) offers a promising potential solution by providing a quick, yet precise, measure of function that can be used across a broad range of patient abilities and in multiple settings. CAT technology yields a precise score by selecting very few relevant items from a large and diverse item pool based on each individual{\textquoteright}s responses. We demonstrate the potential usefulness of a CAT assessment model with a cross-sectional sample of persons with stroke from multiple rehabilitation settings.}, keywords = {*Computer Simulation, *User-Computer Interface, Adult, Aged, Aged, 80 and over, Cerebrovascular Accident/*rehabilitation, Disabled Persons/*classification, Female, Humans, Male, Middle Aged, Monitoring, Physiologic/methods, Severity of Illness Index, Task Performance and Analysis}, isbn = {1074-9357 (Print)}, author = {Andres, P. L. and Black-Schaffer, R. M. and Ni, P. and Haley, S. M.} }