Improved score tests for exponential family nonlinear models. Issue 15 (8th July 2021)

• Record Type: Journal Article
• Authors: Cavalcanti, Alexsandro B.; Botter, Denise A.; Barroso, Lúcia P.; Santos-Neto, Manoel; Cordeiro, Gauss M.
• Is Part Of: Communications in statistics. Volume 50:Issue 15(2021)
• Page Start: 3731
• Page End: 3745
• Publication Date: 2021-07-08
• Subjects: Bartlett-type correction -- exponential family -- Monte Carlo simulation -- nonlinear model -- score test; Mathematical statistics -- Periodicals; Mathematics; Statistics; 519.2
• DOI: 10.1080/03610926.2019.1710202
• Languages: English
• ISSNs: 0361-0926

Abstract

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.