Open AccessON THE LATENT REGRESSION MODEL OF ITEM RESPONSE THEORY
Author(s) -
Antal Tamás
Publication year - 2007
Publication title -
ets research report series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.235
H-Index - 5
ISSN - 2330-8516
DOI - 10.1002/j.2333-8504.2007.tb02054.x
Subject(s) - item response theory , mathematics , regression , gauss , regression analysis , computer science , computerized adaptive testing , standard error , linear regression , statistics , algorithm , econometrics , psychometrics , physics , quantum mechanics
Full account of the latent regression model for the National Assessment of Educational Progress is given. The treatment includes derivation of the EM algorithm, Newton‐Raphson method, and the asymptotic standard errors. The paper also features the use of the adaptive Gauss‐Hermite numerical integration method as a basic tool to evaluate expectations necessary to perform the parameter estimations.