The package provides some tools related to using the Nash variant of Marquardt's algorithm for nonlinear least squares.
John C Nash and Duncan Murdoch
Maintainer: <nashjc@uottawa.ca>
| Package: | nlsr |
| Type: | Package |
| Version: | 1.0 |
| Date: | 2012-03-05 |
| License: | GPL-2 |
This package includes methods for solving nonlinear least squares problems specified by a modeling expression and given a starting vector of named paramters. Note: You must provide an expression of the form lhs ~ rhsexpression so that the residual expression rhsexpression - lhs can be computed. The expression can be enclosed in quotes, and this seems to give fewer difficulties with R. Data variables must already be defined, either within the parent environment or else in the dot-arguments. Other symbolic elements in the modeling expression must be standard functions or else parameters that are named in the start vector.
The main functions in nlsr are:
Nash variant of the Marquardt procedure for nonlinear least squares,
with bounds constraints, using a residual and optionally Jacobian
described as R functions.
Nash variant of the Marquardt procedure for nonlinear least squares,
with bounds constraints, using an expression to describe the residual via
an R modeling expression. The Jacobian is computed via symbolic
differentiation.
Uses nlxb to solve nonlinear least squares then calls nls() to create an object of type nls.
returns a function with header function(prm), which
evaluates the residuals (and if jacobian is TRUE the
Jacobian matrix) of the model at prm. The residuals are defined
to be the right hand side of modelformula minus the left hand side.
returns a function with header function(prm), which
evaluates the sum of squared residuals (and if gradient is TRUE the
gradient vector) of the model at prm.
returns the expression used to calculate the vector of residuals (and possibly the Jacobian) used in the previous functions.
Nash, J. C. (1979, 1990) _Compact Numerical Methods for Computers. Linear Algebra and Function Minimisation._ Adam Hilger./Institute of Physics Publications
Nash, J. C. (2014) _Nonlinear Parameter Optimization Using R Tools._ Wiley
nls