pInf: Parameter Inference for classic nonlinear regression.

In nlr: Nonlinear Regression Modelling using Robust Methods

Description

Parameter inference for classic nonliner regression. It work same as parInfer method of nl.fitt, calculate covariance matrix of parameters and their confidence interval using gradient as design matrix.

Usage

pInf(object, confidence = 0.95)

Arguments

object	Object type nl.fitt or any other of its child objects such as nl.fitt.gn, nl.fitt.rob, nl.fitt.rgn.
confidence	Confidence probability.

Details

For computing the covariance matrix of a nonlinear regression parameter, the gradient of function with respect to parameters is consider as design matrix and linear regression formulas apply for computing covariances and confidence intervals.

Value

covmat:	Covariance matrix of nonlinear model function parameters.
corrmat	Correlation matrix of nonlinear model function parameters.
parstdev:	Standard deviation of nonlinear model function parameter. It is square root of diagonal of covmat.
CI:	Confidence interval for nonlinear model function parameter.

Note

This function implemented for calling for non object purpose, for example computing covarianc matrix for Weighted M-estimate stored as nl.fitt.rgn but using classic covariance computation using gradinet, instead parInfer which use convergence properties (Lim et al. 2010)

This function call by nlr, for compatibility it is better to call from nlr rather than directly by user.

Author(s)

Hossein Riazoshams, Jan 2010. Email: [e-mail] URL http://www.riazoshams.com/nlr/

References

Seber, G., A. F. and Wild, C. J. (2003). Nonlinear Regression. New York: John Wiley & Sons, Inc.

Lim, C., Sen, P. K., Peddada, S. D. (2010). Statistical inference in nonlinear regression under heteroscedasticity. Sankhya B 72:202-218.

See Also

nl.fitt, nl.fitt.gn, nl.fitt.rob, nl.fitt.rgn

Examples

## The function is currently defined as
"pInf"

nlr documentation built on July 31, 2019, 5:09 p.m.