Precision of Warm's Weighted Likelihood Estimates for a Polytomous Model in Computerized Adaptive Testing.

Wang, Shudong; Wang, Tianyou

Notes FAQ Contact Us

Back to results

Peer reviewed

ERIC Number: EJ644199

Record Type: Journal

Publication Date: 2001

Pages: N/A

Abstractor: N/A

ISBN: N/A

ISSN: ISSN-0146-6216

EISSN: N/A

Available Date: N/A

Precision of Warm's Weighted Likelihood Estimates for a Polytomous Model in Computerized Adaptive Testing.

Wang, Shudong; Wang, Tianyou

Applied Psychological Measurement, v25 n4 p317-31 Dec 2001

Evaluated the relative accuracy of the weighted likelihood estimate (WLE) of T. Warm (1989) compared to the maximum likelihood estimate (MLE), expected a posteriori estimate, and maximum a posteriori estimate. Results of the Monte Carlo study, which show the relative advantages of each approach, suggest that the test termination rule has more impact on the accuracy of theta estimation than does the item bank size. (SLD)

Descriptors: Ability, Adaptive Testing, Computer Assisted Testing, Estimation (Mathematics), Item Banks, Maximum Likelihood Statistics, Monte Carlo Methods

Publication Type: Journal Articles; Reports - Evaluative

Education Level: N/A

Audience: N/A

Language: English

Sponsor: N/A

Authoring Institution: N/A

Grant or Contract Numbers: N/A

Author Affiliations: N/A