Bartlett and Bartlett-type corrections in heteroscedastic symmetric nonlinear regression models

Abstract: This paper provides general expression for Bartlett and Bartlett-type correction factors for the likelihood ratio and gradient statistics to test the dispersion parameter in heteroscedastic symmetric nonlinear models. This class of regression models is potentially useful for modeling data containing outlying observations. We consider a partition on the dispersion parameter vector in order to test the parameters of interest. Furthermore, we develop Monte Carlo simulations to compare the finite sample performances of the corrected tests proposed with the usual and modified score tests, likelihood and gradient tests, the Bartlett-type corrected score test and bootstrap corrected tests. Our simulation results favor the score and gradient corrected tests as well as the bootstrap tests. An empirical application is presented for illustrative purposes.