scientific article; zbMATH DE number 1165672

MaRDI QIDQ4396378zbMATH OpenFDO

Authors Silvelyn Zwanzig, O. V. Ivanov

Publication date 14 June 1998

zbMATH Keywords

chi-square distributionsaddlepoint approximation

Mathematics Subject Classification ID

Asymptotic distribution theory in statistics (62E20) General nonlinear regression (62J02)

Review text

The authors consider the nonlinear regression model \(y_t=g(x_t,\beta )+\varepsilon_t,\;t=1,\dots,n\), where \(\varepsilon_1,\dots,\varepsilon_n\) are i.i.d. unobservable normally distributed errors with zero mean and variance \(\sigma^2.\) The regression function \(g(\cdot)\) and the design points \(x_1,\dots,x_n \in [0,1]\) are known. The residual sum of squares \[ RSS=\min_{\beta}{{1}\over{n}}\sum_{t=1}^n(y_t-g(x_t,\beta))^2 \] is investigated. It is shown that the saddlepoint approximation of first order for the distribution of \(RSS\) is a \(\chi^2\) distribution.

Recommendations

• Some properties and improvements of the saddlepoint approximation in nonlinear regression
• Saddlepoint approximations for estimating equations
• Saddlepoint approximation of nonlinear moments
• Saddlepoint approximations
• Saddlepoint approximations for nonlinear statistics
• Saddlepoint approximation

Cited in

(3)

• Saddlepoint expansions in linear regression.
• Some properties and improvements of the saddlepoint approximation in nonlinear regression
• scientific article; zbMATH DE number 1995706 (Why is no real title available?)

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4396378)