Three Multidimensional Models for Testlet-Based Tests: Formal Relations and an Empirical Comparison. Research Report. ETS RR-09-37.

Three multidimensional item response theory (IRT) models for testlet-based tests are described. In the bifactor model (Gibbons & Hedeker, 1992), each item measures a general dimension in addition to a testlet-specific dimension. The testlet model (Bradlow, Wainer, & Wang, 1999) is a bifactor model in which the loadings on the specific dimensions are restricted to be proportional to the loadings on the general dimension within each testlet (Li, Bolt, & Fu, 2006). In the second-order model, the items only load on the testlet-specific factors. The correlations between the testlet-specific factors are modeled through a second-order factor. The second-order model is formally equivalent to the testlet model. The models were applied to a testlet-based international English assessment test.

[1]  Daniel M. Bolt,et al.  A Comparison of Alternative Models for Testlets , 2006 .

[2]  John Schmid,et al.  The development of hierarchical factor solutions , 1957 .

[3]  R. D. Bock,et al.  Marginal maximum likelihood estimation of item parameters: Application of an EM algorithm , 1981 .

[4]  I. Meilijson.  A fast improvement to the EM algorithm on its own terms , 1989 .

[5]  Frank Rijmen,et al.  Efficient Full Information Maximum Likelihood Estimation for Multidimensional IRT Models. Research Report. ETS RR-09-03. , 2009 .

[6]  L. Fahrmeir,et al.  Multivariate statistical modelling based on generalized linear models , 1994 .

[7]  David Thissen,et al.  On the relationship between the higher-order factor model and the hierarchical factor model , 1999 .

[8]  B. Muthén.  A general structural equation model with dichotomous, ordered categorical, and continuous latent variable indicators , 1984 .

[9]  R. D. Bock,et al.  Marginal maximum likelihood estimation of item parameters , 1982 .

[10]  Donald Hedeker,et al.  Full-information item bi-factor analysis , 1992 .

[11]  Eric T. Bradlow,et al.  A Bayesian random effects model for testlets , 1999 .

[12]  Paul De Boeck,et al.  Latent Class Models for Diary Method Data: Parameter Estimation by Local Computations , 2007, Psychometrika.

[13]  Jan de Leeuw,et al.  On the relationship between item response theory and factor analysis of discretized variables , 1987 .

[14]  Eric R. Ziegel,et al.  Multivariate Statistical Modelling Based on Generalized Linear Models , 2002, Technometrics.

[15]  Karl G. Jöreskog,et al.  On the estimation of polychoric correlations and their asymptotic covariance matrix , 1994 .