Abstract
This paper focuses on the corrections to the score test statistic under the exponential family nonlinear model. We use Monte Carlo simulations to compare the corrected statistics and their uncorrected versions and to examine the impact of the number of nuisance parameters on their finite-sample behaviors for the normal nonlinear regression model. The numerical results have shown that the corrected score statistic performs better than the uncorrected version. Finally, we perform a statistical analysis with real data by using the approach proposed in the article.
Acknowledgments
This paper is based on part of Cavalcanti’s doctoral thesis submitted to the Instituto de Matemática e Estatística, Universidade de São Paulo, under the supervision of the second author. The authors thank the Editors and referees for their constructive comments on an earlier version of this manuscript which resulted in this improved version. Also, we thank Prof. Dr. Michelli Barros (UFCG) for valuable help in simulation program.
A. Cumulants of log-likelihood derivatives in exponential family nonlinear models
Let be the log-likelihood (Equation4
(4)
(4) ). We hall use the standard notation for joint cumulants of log-likelihood derivatives, i.e.,
and so on. We obtain the following cumulants:
where
and
for
and
The third-order cumulants are
where
for
and
and the quantities
and
are defined by EquationEquations (4)
(4)
(4) and Equation(9)
(9)
(9) , respectively. Further, the fourth-order cumulants are given by
where
for
and
and the quantities
and
defined by EquationEquations (9)
(9)
(9) and Equation(10)
(10)
(10) , respectively.
The equation gives
and
where
and so on, gives
and
for
Thus we obtain the following cumulants
B. Cumulants for the Bartlett correction factor
B.1. Tests for components of β and δ
Suppose that we want to test the null hypothesis versus
Then, the coefficients for the Bartlett-type corrections can be expressed terms
B.2. Tests for components of δ
Here, suppose that we want to test the null hypothesis versus
In this situation, just consider
and then the coefficients of the corrected score reduce to
Further, for testing all the components of
we have
Hence,
B.3. Tests for components of β
Finally, suppose that we want to test the null hypothesis versus
If we consider
then the coefficients of the corrected score statistic are
Finally, for testing all the components of
we have
Hence,