Profile.covariance {CollocInfer} | R Documentation |
Profile.covariance
Description
Newey-West estimate of covariance of parameter estimates from profiling.
Usage
Profile.covariance(pars,active=NULL,times,data,coefs,lik,proc,
in.meth='nlminb',control.in=NULL,eps=1e-6,GN=FALSE)
Arguments
pars |
Initial values of parameters to be estimated processes. |
active |
Incides indicating which parameters of |
times |
Vector observation times for the data. |
data |
Matrix of observed data values. |
coefs |
Vector giving the current estimate of the coefficients in the spline. |
lik |
|
proc |
|
in.meth |
Inner optimization function currently one of 'nlminb', 'MaxNR', 'optim' or 'house'. The last calls |
control.in |
Control object for inner optimization functions. |
eps |
Step-size for finite difference estimate of second derivatives. |
GN |
Indicator of whether a Gauss-Newton approximation for the Hessian should be employed. Only valid for least-squares methods. |
Details
Currently assumes a lag-5 auto-correlation among observation vectors.
Value
Returns a Newey-West estimate of the covariance matrix of the parameter estimates.
See Also
ProfileErr
, ProfileSSE
, Profile.LS
, Profile.multinorm
Examples
# See example in Profile.LS