Open Conference Systems, 50th Scientific meeting of the Italian Statistical Society

Font Size: 
A regularized estimation approach for the three-parameter logistic model
Michela Battauz, Ruggero Bellio

Last modified: 2018-06-25

Abstract


The three-parameter logistic model is an item response theory model

used with dichotomous items. It is well known that the parameters of

the model are weekly identifiable and that the maximization of the

likelihood, which is performed using numerical algorithms, is prone to

convergence issues. In this paper, we propose the use of a penalized likelihood

for the estimation of the item parameters. In particular, the penalty term

shrinks the guessing parameter toward a known constant.

Cross-validation is used to select such constant and the amount of shrinkage.

The method is both simple and effective, and it is illustrated by means of

a real data example.

 


References


1. Bock, R. D., Aitkin, M.: Marginal maximum likelihood estimation of item parameters: Applicationof an EM algorithm. Psychometrika. 46, 443–459 (1981)

2. Chalmers, R.: mirt: A Multidimensional Item Response Theory Package for the R Environment.Journal of Statistical Software. 48, 1–29 (2012)

3. Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning (2nd Edition).Springer, New York (2009)

4. Kosmidis, I., and Firth, D. (2010). A generic algorithm for reducing bias in parametric estimation.Electron. J. Statist., 4, 1097–1112 (2010)

5. Murdoch, D. and Chow, E. D. ellipse: Functions for drawing ellipses and ellipse-like confidenceregions. R package version 0.3-8 (2013)

6. Patz, R. J., Junker, B.W.: Applications and extensions of MCMC in IRT: Multiple item types,missing data, and rated responses. J. Educ. Behav. Stat. 24, 342–366 (1999)

7. R Core Team: R: A language and environment for statistical computing. R Foundation forStatistical Computing, Vienna, Austria (2017)

8. Tutz, G: Regression for Categorical Data. Cambridge University Press, Cambridge (2011)

9. Woods, C.: Estimating the latent density in unidimensional IRT to permit non-normality. In:Reise, S. P., and Revicki, D. A. (Eds.) Measuring Psychological Constructs: Advances inModel-Based Approaches, pp. 60–84. Routledge, New York (2015)


Full Text: PDF