New methods of testing nonlinear hypothesis using iterative NLLS estimator

14th International Conference on Science, Engineering and Technology

自然科学;工业技术

Mahaboob, B.^1 ; Venkateswarlu, B.^2 ; Mokeshrayalu, G.^2 ; Balasiddamuni, P.^3

Department of Mathematics, Swetha Institute of Technology and Science, Tirupati

Andhra Pradesh, India^1

Department of Mathematics, School of Advanced Sciences, VIT University, Vellore

632014, India^2

Department of Statistics, S.V.University, Tirupati

Andhra Pradesh, India^3

关键词: Asymptotic properties;    Composite hypothesis;    Least absolute deviations;    Multiple hypothesis;    Non-linear least squares;    Nonlinear regression models;    Statistical testing;    Studentized residuals;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/263/4/042126/pdf
DOI  :  10.1088/1757-899X/263/4/042126

来源: IOP

【 摘 要 】

This research paper discusses the method of testing nonlinear hypothesis using iterative Nonlinear Least Squares (NLLS) estimator. Takeshi Amemiya [1] explained this method. However in the present research paper, a modified Wald test statistic due to Engle, Robert [6] is proposed to test the nonlinear hypothesis using iterative NLLS estimator. An alternative method for testing nonlinear hypothesis using iterative NLLS estimator based on nonlinear hypothesis using iterative NLLS estimator based on nonlinear studentized residuals has been proposed. In this research article an innovative method of testing nonlinear hypothesis using iterative restricted NLLS estimator is derived. Pesaran and Deaton [10] explained the methods of testing nonlinear hypothesis. This paper uses asymptotic properties of nonlinear least squares estimator proposed by Jenrich [8]. The main purpose of this paper is to provide very innovative methods of testing nonlinear hypothesis using iterative NLLS estimator, iterative NLLS estimator based on nonlinear studentized residuals and iterative restricted NLLS estimator. Eakambaram et al. [12] discussed least absolute deviation estimations versus nonlinear regression model with heteroscedastic errors and also they studied the problem of heteroscedasticity with reference to nonlinear regression models with suitable illustration. William Grene [13] examined the interaction effect in nonlinear models disused by Ai and Norton [14] and suggested ways to examine the effects that do not involve statistical testing. Peter [15] provided guidelines for identifying composite hypothesis and addressing the probability of false rejection for multiple hypotheses.