Events and Meetings of Italian Statistical Society, Advances in Latent Variables - Methods, Models and Applications

Font Size: 
Simple Linear Measurement Error Model estimated via Generalized Maximum Entropy for Ordinal Data
Enrico Ciavolino

Last modified: 2013-06-14

Abstract


The aim of this paper is the evaluation of the non-linearity existing in homogeneous ordinal data with a one-dimensional latent variable, using a Simple Linear Measurement Error Model based on Generalized Maximum Entropy. A Monte Carlo simulation study is proposed for comparing the performances of the proposed estimator to his counterpart the Ordinary Least Squares Adjusted for attenuation, in case the data are affected by the non-linearity. The two estimators are compared in term of correlation with the true latent variable, standard error and root mean of squared error.

Full Text: PDF