%0 Journal Article
%J Journal of Educational Measurement
%D 2006
%T Comparing methods of assessing differential item functioning in a computerized adaptive testing environment
%A Lei, P-W.
%A Chen, S-Y.
%A Yu, L.
%K computerized adaptive testing
%K educational testing
%K item response theory likelihood ratio test
%K logistic regression
%K trait estimation
%K unidirectional & non-unidirectional differential item functioning
%X Mantel-Haenszel and SIBTEST, which have known difficulty in detecting non-unidirectional differential item functioning (DIF), have been adapted with some success for computerized adaptive testing (CAT). This study adapts logistic regression (LR) and the item-response-theory-likelihood-ratio test (IRT-LRT), capable of detecting both unidirectional and non-unidirectional DIF, to the CAT environment in which pretest items are assumed to be seeded in CATs but not used for trait estimation. The proposed adaptation methods were evaluated with simulated data under different sample size ratios and impact conditions in terms of Type I error, power, and specificity in identifying the form of DIF. The adapted LR and IRT-LRT procedures are more powerful than the CAT version of SIBTEST for non-unidirectional DIF detection. The good Type I error control provided by IRT-LRT under extremely unequal sample sizes and large impact is encouraging. Implications of these and other findings are discussed. all rights reserved)
%B Journal of Educational Measurement
%I Blackwell Publishing: United Kingdom
%V 43
%P 245-264
%@ 0022-0655 (Print)
%G eng
%M 2006-10742-004
%0 Journal Article
%J Applied Psychological Measurement
%D 2005
%T Controlling item exposure and test overlap in computerized adaptive testing
%A Chen, S-Y.
%A Lei, P-W.
%K Adaptive Testing
%K Computer Assisted Testing
%K Item Content (Test) computerized adaptive testing
%X This article proposes an item exposure control method, which is the extension of the Sympson and Hetter procedure and can provide item exposure control at both the item and test levels. Item exposure rate and test overlap rate are two indices commonly used to track item exposure in computerized adaptive tests. By considering both indices, item exposure can be monitored at both the item and test levels. To control the item exposure rate and test overlap rate simultaneously, the modified procedure attempted to control not only the maximum value but also the variance of item exposure rates. Results indicated that the item exposure rate and test overlap rate could be controlled simultaneously by implementing the modified procedure. Item exposure control was improved and precision of trait estimation decreased when a prespecified maximum test overlap rate was stringent. (PsycINFO Database Record (c) 2005 APA ) (journal abstract)
%B Applied Psychological Measurement
%V 29
%P 204-217
%G eng
%0 Journal Article
%J Journal of Educational Measurement
%D 2004
%T Effects of practical constraints on item selection rules at the early stages of computerized adaptive testing
%A Chen, S-Y.
%A Ankenmann, R. D.
%K computerized adaptive testing
%K item selection rules
%K practical constraints
%X The purpose of this study was to compare the effects of four item selection rules--(1) Fisher information (F), (2) Fisher information with a posterior distribution (FP), (3) Kullback-Leibler information with a posterior distribution (KP), and (4) completely randomized item selection (RN)--with respect to the precision of trait estimation and the extent of item usage at the early stages of computerized adaptive testing. The comparison of the four item selection rules was carried out under three conditions: (1) using only the item information function as the item selection criterion; (2) using both the item information function and content balancing; and (3) using the item information function, content balancing, and item exposure control. When test length was less than 10 items, FP and KP tended to outperform F at extreme trait levels in Condition 1. However, in more realistic settings, it could not be concluded that FP and KP outperformed F, especially when item exposure control was imposed. When test length was greater than 10 items, the three nonrandom item selection procedures performed similarly no matter what the condition was, while F had slightly higher item usage. (PsycINFO Database Record (c) 2007 APA, all rights reserved)
%B Journal of Educational Measurement
%I Blackwell Publishing: United Kingdom
%V 41
%P 149-174
%@ 0022-0655 (Print)
%G eng
%M 2005-04771-004
%0 Journal Article
%J Journal of Educational Measurement
%D 2003
%T The relationship between item exposure and test overlap in computerized adaptive testing
%A Chen, S-Y.
%A Ankemann, R. D.
%A Spray, J. A.
%K (Statistical)
%K Adaptive Testing
%K Computer Assisted Testing
%K Human Computer
%K Interaction computerized adaptive testing
%K Item Analysis
%K Item Analysis (Test)
%K Test Items
%X The purpose of this article is to present an analytical derivation for the mathematical form of an average between-test overlap index as a function of the item exposure index, for fixed-length computerized adaptive tests (CATs). This algebraic relationship is used to investigate the simultaneous control of item exposure at both the item and test levels. The results indicate that, in fixed-length CATs, control of the average between-test overlap is achieved via the mean and variance of the item exposure rates of the items that constitute the CAT item pool. The mean of the item exposure rates is easily manipulated. Control over the variance of the item exposure rates can be achieved via the maximum item exposure rate (r-sub(max)). Therefore, item exposure control methods which implement a specification of r-sub(max) (e.g., J. B. Sympson and R. D. Hetter, 1985) provide the most direct control at both the item and test levels. (PsycINFO Database Record (c) 2005 APA )
%B Journal of Educational Measurement
%V 40
%P 129-145
%G eng
%0 Journal Article
%J Applied Psychological Measurement
%D 2000
%T A comparison of item selection rules at the early stages of computerized adaptive testing
%A Chen, S-Y.
%A Ankenmann, R. D.
%A Chang, Hua-Hua
%K Adaptive Testing
%K Computer Assisted Testing
%K Item Analysis (Test)
%K Statistical Estimation computerized adaptive testing
%X The effects of 5 item selection rules--Fisher information (FI), Fisher interval information (FII), Fisher information with a posterior distribution (FIP), Kullback-Leibler information (KL), and Kullback-Leibler information with a posterior distribution (KLP)--were compared with respect to the efficiency and precision of trait (θ) estimation at the early stages of computerized adaptive testing (CAT). FII, FIP, KL, and KLP performed marginally better than FI at the early stages of CAT for θ=-3 and -2. For tests longer than 10 items, there appeared to be no precision advantage for any of the selection rules. (PsycINFO Database Record (c) 2005 APA ) (journal abstract)
%B Applied Psychological Measurement
%V 24
%P 241-255
%G eng