Testing the linear errors-in-variables model with randomly censored data

This paper considers the testing problem of the linear errors-in-variables (EV) model with random censored data. We propose two novel statistics based on the difference between the corrected residual sum of squares (RSS) and empirical likelihood (EL) under the null and alternative hypotheses. Based on adjusted statistics, we develop two testing procedures for the linear EV model with random censoring. Simulation studies and data analysis are conducted to evaluate the small sample performances of the proposed methods.