Email this article Missing data and parameters estimates in multidimensional item response models
Abstract
Survey based analyses usually face the problem of missing data. Certain statistical methods require a full data matrix to be provided, in order to be applicable, hence the need to cope with such missingness. Literature on imputation abounds with contributions concerning quantitative responses, but seems to be poor with respect to the handling of categorical data. The present work aims to evaluate the impact of different imputation methods on multidimensional IRT models estimation.
References
. Little, R.J.A and Rubin, D.B. (1987). Statistical analysis with missing data. New York: John Wiley.
. Ferrari, P.A., Annoni, P., Barbiero, A. and Manzi, G. (2011). An imputation method for categorical variables with application to nonlinear principal component analysis. Computational Statistics and Data Analysis, 55, 2410–2420.
. Reckase, M.D. (2009). Multidimensional Item Response Theory. Springer, New York.
. Stekhoven, D.J. and Bühlmann, P. (2012). MissForest—non-parametric missing value imputation for mixed-type data. Bioinformatics, vol. 28, no. 1, 112–118.
. van Buuren, S., Brand, J.P.L., Groothuis-Oudshoorn, C.G.M. and Rubin, D.B. (2006). Fully conditional specification in multivariate imputation. Journal of Statistical Computation and Simulation, 76(12), 1049-1064.
. Kennett, R.S. and Salini, S. (2012). Modern analysis of customer surveys: with applications using R. New York: John Wiley.
. Andreis, F. and Ferrari, P.A. (2012). Multidimensional extensions of IRT models and their application to customer satisfaction evaluation, in MMLV2012, Napoli, 17-19 May 2012, 5-8.
. Finch, H. (2008). Estimation of Item Response Theory Parameters in the Presence of Missing Data. Journal of Educational Measurement, 45: 225–245.
. Jackman, S. (2001). Multidimensional analysis of roll call data via Bayesian simulation: identification, estimation, inference and model checking. Political Analysis, 9(3): 227-241.
Full Text: PDF
