covariance matrix and proposal matrix

Use of Healpix, camb, CLASS, cosmomc, compilers, etc.
Post Reply
Feng-Quan Wu
Posts: 7
Joined: July 25 2007
Affiliation: The National Astronomical Observatories, Chinese Academy of Science

covariance matrix and proposal matrix

Post by Feng-Quan Wu » June 13 2008

Is the covariance matrix(outputting file of CosmoMC, eg.
test.covmat) the invertion of Fisher matrix at the best fitting
point?

I'm confused, because the params.ini says one "can use covariance
matrix for proposal density", but I think the covariance matrix
derived from Fisher matrix is very different from the proposal
matrix in the MCMC technology.

Antony Lewis
Posts: 1501
Joined: September 23 2004
Affiliation: University of Sussex
Contact:

Re: covariance matrix and proposal matrix

Post by Antony Lewis » June 13 2008

It is the covariance matrix of the samples.

If supplied for an MCMC run it is used to construct a decent proposal matrix that knows about parameter scales and correlations.

Feng-Quan Wu
Posts: 7
Joined: July 25 2007
Affiliation: The National Astronomical Observatories, Chinese Academy of Science

covariance matrix and proposal matrix

Post by Feng-Quan Wu » June 14 2008

I see, thank you very much!

Post Reply