geoR

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

geoR

Ruben Roa
-----Original Message-----
From: r-sig-geo-bounces at stat.math.ethz.ch on behalf of Ole F. Christensen
Sent: Fri 3/4/2005 3:53 PM
To: Anders Malmberg
Cc: R-sig-Geo at stat.math.ethz.ch
Subject: Re: [R-sig-Geo] geoR
Dear Anders

* The maximum likelihood estimate of the partial sill parameter sigmasq
can be expressed explictly as function of the other covariance parameters.
Therefore parameter estimate for sigmasq is NOT found by numerical
maximisation, and as consequence in likfit you cannot specify that that
sigmasq should be within certain limits.

* The parameter estimate for the relative nugget tausq.rel is found by
numerical maximisation. Therefore you can specify that this parameter
should be within certain limits.

Best

Ole

----------------
I understand that the range parameter phi is also a 'free parameter'. Am i correct?

Another quick question: i haven't been able to obtain the estimation variance of the phi parameter estimate as i do for the beta estimate with likfitobject$beta.var. What is the necessary command?
Cheers

Ruben

[snip Anders Malmberg's original question]



Reply | Threaded
Open this post in threaded view
|

geoR

Ole F. Christensen
Yes, the ``range parameter'' phi is a free parameter.
Calculation of variance of the estimate for phi  is not implemented in
function likfit.
Instead you should use the proflik function to obtain the profile
likelihood for this parameter.

Ole

Ruben Roa wrote:

>-----Original Message-----
>From: r-sig-geo-bounces at stat.math.ethz.ch on behalf of Ole F. Christensen
>Sent: Fri 3/4/2005 3:53 PM
>To: Anders Malmberg
>Cc: R-sig-Geo at stat.math.ethz.ch
>Subject: Re: [R-sig-Geo] geoR
>Dear Anders
>
>* The maximum likelihood estimate of the partial sill parameter sigmasq
>can be expressed explictly as function of the other covariance parameters.
>Therefore parameter estimate for sigmasq is NOT found by numerical
>maximisation, and as consequence in likfit you cannot specify that that
>sigmasq should be within certain limits.
>
>* The parameter estimate for the relative nugget tausq.rel is found by
>numerical maximisation. Therefore you can specify that this parameter
>should be within certain limits.
>
>Best
>
>Ole
>
>----------------
>I understand that the range parameter phi is also a 'free parameter'. Am i correct?
>
>Another quick question: i haven't been able to obtain the estimation variance of the phi parameter estimate as i do for the beta estimate with likfitobject$beta.var. What is the necessary command?
>Cheers
>
>Ruben
>
>[snip Anders Malmberg's original question]
>
>_______________________________________________
>R-sig-Geo mailing list
>R-sig-Geo at stat.math.ethz.ch
>https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>
>
>  
>

--
Ole F. Christensen
BiRC - Bioinformatics Research Center
University of Aarhus