@article {84, title = {Letting the CAT out of the bag: Comparing computer adaptive tests and an 11-item short form of the Roland-Morris Disability Questionnaire}, journal = {Spine}, volume = {33}, number = {12}, year = {2008}, note = {Cook, Karon FChoi, Seung WCrane, Paul KDeyo, Richard AJohnson, Kurt LAmtmann, Dagmar5 P60-AR48093/AR/United States NIAMS5U01AR052171-03/AR/United States NIAMSComparative StudyResearch Support, N.I.H., ExtramuralUnited StatesSpineSpine. 2008 May 20;33(12):1378-83.}, month = {May 20}, pages = {1378-83}, edition = {2008/05/23}, abstract = {STUDY DESIGN: A post hoc simulation of a computer adaptive administration of the items of a modified version of the Roland-Morris Disability Questionnaire. OBJECTIVE: To evaluate the effectiveness of adaptive administration of back pain-related disability items compared with a fixed 11-item short form. SUMMARY OF BACKGROUND DATA: Short form versions of the Roland-Morris Disability Questionnaire have been developed. An alternative to paper-and-pencil short forms is to administer items adaptively so that items are presented based on a person{\textquoteright}s responses to previous items. Theoretically, this allows precise estimation of back pain disability with administration of only a few items. MATERIALS AND METHODS: Data were gathered from 2 previously conducted studies of persons with back pain. An item response theory model was used to calibrate scores based on all items, items of a paper-and-pencil short form, and several computer adaptive tests (CATs). RESULTS: Correlations between each CAT condition and scores based on a 23-item version of the Roland-Morris Disability Questionnaire ranged from 0.93 to 0.98. Compared with an 11-item short form, an 11-item CAT produced scores that were significantly more highly correlated with scores based on the 23-item scale. CATs with even fewer items also produced scores that were highly correlated with scores based on all items. For example, scores from a 5-item CAT had a correlation of 0.93 with full scale scores. Seven- and 9-item CATs correlated at 0.95 and 0.97, respectively. A CAT with a standard-error-based stopping rule produced scores that correlated at 0.95 with full scale scores. CONCLUSION: A CAT-based back pain-related disability measure may be a valuable tool for use in clinical and research contexts. Use of CAT for other common measures in back pain research, such as other functional scales or measures of psychological distress, may offer similar advantages.}, keywords = {*Disability Evaluation, *Health Status Indicators, Adult, Aged, Aged, 80 and over, Back Pain/*diagnosis/psychology, Calibration, Computer Simulation, Diagnosis, Computer-Assisted/*standards, Humans, Middle Aged, Models, Psychological, Predictive Value of Tests, Questionnaires/*standards, Reproducibility of Results}, isbn = {1528-1159 (Electronic)}, author = {Cook, K. F. and Choi, S. W. and Crane, P. K. and Deyo, R. A. and Johnson, K. L. and Amtmann, D.} } @article {328, title = {Psychometric evaluation and calibration of health-related quality of life item banks: plans for the Patient-Reported Outcomes Measurement Information System (PROMIS)}, journal = {Medical Care}, volume = {45}, number = {5 Suppl 1}, year = {2007}, note = {Reeve, Bryce BHays, Ron DBjorner, Jakob BCook, Karon FCrane, Paul KTeresi, Jeanne AThissen, DavidRevicki, Dennis AWeiss, David JHambleton, Ronald KLiu, HonghuGershon, RichardReise, Steven PLai, Jin-sheiCella, DavidPROMIS Cooperative GroupAG015815/AG/United States NIAResearch Support, N.I.H., ExtramuralUnited StatesMedical careMed Care. 2007 May;45(5 Suppl 1):S22-31.}, month = {May}, pages = {S22-31}, edition = {2007/04/20}, abstract = {BACKGROUND: The construction and evaluation of item banks to measure unidimensional constructs of health-related quality of life (HRQOL) is a fundamental objective of the Patient-Reported Outcomes Measurement Information System (PROMIS) project. OBJECTIVES: Item banks will be used as the foundation for developing short-form instruments and enabling computerized adaptive testing. The PROMIS Steering Committee selected 5 HRQOL domains for initial focus: physical functioning, fatigue, pain, emotional distress, and social role participation. This report provides an overview of the methods used in the PROMIS item analyses and proposed calibration of item banks. ANALYSES: Analyses include evaluation of data quality (eg, logic and range checking, spread of response distribution within an item), descriptive statistics (eg, frequencies, means), item response theory model assumptions (unidimensionality, local independence, monotonicity), model fit, differential item functioning, and item calibration for banking. RECOMMENDATIONS: Summarized are key analytic issues; recommendations are provided for future evaluations of item banks in HRQOL assessment.}, keywords = {*Health Status, *Information Systems, *Quality of Life, *Self Disclosure, Adolescent, Adult, Aged, Calibration, Databases as Topic, Evaluation Studies as Topic, Female, Humans, Male, Middle Aged, Outcome Assessment (Health Care)/*methods, Psychometrics, Questionnaires/standards, United States}, isbn = {0025-7079 (Print)}, author = {Reeve, B. B. and Hays, R. D. and Bjorner, J. B. and Cook, K. F. and Crane, P. K. and Teresi, J. A. and Thissen, D. and Revicki, D. A. and Weiss, D. J. and Hambleton, R. K. and Liu, H. and Gershon, R. C. and Reise, S. P. and Lai, J. S. and Cella, D.} } @article {2074, title = {Simulated computerized adaptive test for patients with shoulder impairments was efficient and produced valid measures of function}, journal = {Journal of Clinical Epidemiology}, volume = {59}, year = {2006}, pages = {290-298}, abstract = {

Background and Objective: To test unidimensionality and local independence of a set of shoulder functional status (SFS) items,
develop a computerized adaptive test (CAT) of the items using a rating scale item response theory model (RSM), and compare discriminant validity of measures generated using all items (qIRT) and measures generated using the simulated CAT (qCAT).
Study Design and Setting: We performed a secondary analysis of data collected prospectively during rehabilitation of 400 patients
with shoulder impairments who completed 60 SFS items.
Results: Factor analytic techniques supported that the 42 SFS items formed a unidimensional scale and were locally independent. Except for five items, which were deleted, the RSM fit the data well. The remaining 37 SFS items were used to generate the CAT. On average, 6 items on were needed to estimate precise measures of function using the SFS CAT, compared with all 37 SFS items. The qIRT and qCAT measures were highly correlated (r 5 .96) and resulted in similar classifications of patients.
Conclusion: The simulated SFS CAT was efficient and produced precise, clinically relevant measures of functional status with good
discriminating ability.\ 

}, keywords = {computerized adaptive testing, Flexilevel Scale of Shoulder Function, Item Response Theory, Rehabilitation}, author = {Hart, D. L. and Cook, K. F. and Mioduski, J. E. and Teal, C. R. and Crane, P. K.} } @article {85, title = {Dynamic assessment of health outcomes: Time to let the CAT out of the bag?}, journal = {Health Services Research}, volume = {40}, number = {5, part2}, year = {2005}, pages = {1694-1711}, publisher = {Blackwell Publishing: United Kingdom}, abstract = {Background: The use of item response theory (IRT) to measure self-reported outcomes has burgeoned in recent years. Perhaps the most important application of IRT is computer-adaptive testing (CAT), a measurement approach in which the selection of items is tailored for each respondent. Objective. To provide an introduction to the use of CAT in the measurement of health outcomes, describe several IRT models that can be used as the basis of CAT, and discuss practical issues associated with the use of adaptive scaling in research settings. Principal Points: The development of a CAT requires several steps that are not required in the development of a traditional measure including identification of "starting" and "stopping" rules. CAT{\textquoteright}s most attractive advantage is its efficiency. Greater measurement precision can be achieved with fewer items. Disadvantages of CAT include the high cost and level of technical expertise required to develop a CAT. Conclusions: Researchers, clinicians, and patients benefit from the availability of psychometrically rigorous measures that are not burdensome. CAT outcome measures hold substantial promise in this regard, but their development is not without challenges. (PsycINFO Database Record (c) 2007 APA, all rights reserved)}, keywords = {computer adaptive testing, Item Response Theory, self reported health outcomes}, isbn = {0017-9124 (Print); 1475-6773 (Electronic)}, author = {Cook, K. F. and O{\textquoteright}Malley, K. J. and Roddey, T. S.} }