NotesFAQContact Us
Collection
Advanced
Search Tips
Back to results
Peer reviewed Peer reviewed
ERIC Number: EJ381189
Record Type: Journal
Publication Date: 1988
Pages: N/A
Abstractor: N/A
ISBN: N/A
ISSN: N/A
EISSN: N/A
Item Parameter Estimation via Marginal Maximum Likelihood and an EM Algorithm: A Didactic.
Harwell, Michael R.; And Others
Journal of Educational Statistics, v13 n3 p243-71 Fall 1988
The Bock and Aitkin Marginal Maximum Likelihood/EM (MML/EM) approach to item parameter estimation is an alternative to the classical joint maximum likelihood procedure of item response theory. This paper provides the essential mathematical details of a MML/EM solution and shows its use in obtaining consistent item parameter estimates. (TJH)
Descriptors: Algorithms, Computer Software, Equations (Mathematics), Estimation (Mathematics), Latent Trait Theory, Maximum Likelihood Statistics, Programing
Publication Type: Journal Articles; Reports - Research; Computer Programs
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A
Grant or Contract Numbers: N/A