inneropt {CollocInfer} R Documentation

## Inner Optimization Functions

### Description

Estmates coefficients given parameters.

### Usage

inneropt(data,times,pars,coefs,lik,proc,in.meth='nlminb',control.in=list())


### Arguments

 data Matrix of observed data values. times Vector observation times for the data. pars Initial values of parameters to be estimated processes. coefs Vector giving the current estimate of the coefficients in the spline. lik lik object defining the observation process. proc proc object defining the state process. in.meth Inner optimization function currently one of 'nlminb', 'maxNR', 'optim', 'trust' or 'SplineEst'. The last calls SplineEst.NewtRaph. This is fast but has poor convergence. control.in Control object for inner optimization function.

### Details

This minimizes the objective function defined by the addition of the lik and proc objectives with respect to the coefficients. A number of generic optimization routines can be used and some experimentation is recommended.

### Value

A list with elements

 coefs A matrix giving he optimized coefficients. res The results of the inner optimization function.

outeropt, Smooth.LS,LS.setup, multinorm.setup, SplineCoefsErr

### Examples

## Not run:
# FitzHugh-Nagumo Equations

data(FhNdata)   # Some data

knots = seq(0,20,0.2)         # Create a basis
norder = 3
nbasis = length(knots) + norder - 2
range = c(0,20)

bbasis = create.bspline.basis(range=range(FhNtimes),nbasis=nbasis,
norder=norder,breaks=knots)

lambda = 10000               # Penalty value

DEfd = smooth.basis(FhNtimes,FhNdata,fdPar(bbasis,1,0.5))   # Smooth to estimate
# coefficients first
coefs = DEfd$fd$coefs
colnames(coefs) = FhNvarnames

profile.obj = LS.setup(pars=FhNpars,coefs=coefs,fn=make.fhn(),
basisvals=bbasis,lambda=lambda,times=FhNtimes)

lik = profile.obj$lik proc= profile.obj$proc

res = inneropt(FhNdata,times=FhNtimes,FhNpars,coefs,lik,proc,in.meth='nlminb')

plot(fd(res\$coefs,bbasis))

## End(Not run)

[Package CollocInfer version 1.0.4 Index]