fix.parameters: Keeping selected parameters constant during model fitting...

In claus-e-andersen/clanOptim: R functions for non-linear fitting using the optim function from MASS

Description

To facilitate parameter fitting using optim() when some of the parameters are ocationally held constant. optim is from the MASS library. Notes: The p.fixed names can be given in any order and only the number in the names count. For example, p2=3.14 is equivalent to ffffff2=3.14.

Usage

fix.parameters(c(10,30,40),list(p5=50, p2=20)) # gives 10 20 30 40 50
  fix.parameters(NULL,list(p1=20))        # gives 20
  fix.parameters(c(10,20),list(p3=30))    # gives 10 20 30
  fix.parameters(c(10,20),list(p5=30))    # error - there is no 5th parameter
  fix.parameters(c(10,20),list(p3=30,x3=45))  # error - cant refer to the 3rd parameter more than once

Arguments

p	is a vector with parameters (to be fitted)
p.fixed	is a list with fixed parameters (named p1, p2 etc.)
p.fixed.overwrite	is the value to use for all the fixed parameters. When is this useful? It is useful when manupulating the standard error vector when all the positions with fixed parameters should be set to zero or NA. For exampel assume pp and ss are the fitted parameters and std. errors obtained with pfix = list(p2=33.2, p3=5.5). To get the full parameter set and the correspopnding std. errors we simply calculate fixed.parameters(pp, pfix) fixed.parameters(ss,pfix, p.fixed.overwrite=NA).

Value

A merged parameter vector

Author(s)

Claus E. Andersen

claus-e-andersen/clanOptim documentation built on April 16, 2020, 5:21 p.m.