parameter covariance

Home > Statistics Every Writer Should Know > The Stats Board > Discusssion

parameter covariance
Message posted by YYe on October 11, 2000 at 12:00 AM (ET)

Hi everyone,

Could you kindly tell me how the covariance matrix of the estimated paramters is calculated, in either linear or nonlinear regressoin?
Many thanks

READERS RESPOND:
(In chronological order. Most recent at the bottom.)

Re: parameter covariance
Message posted by SOF on October 11, 2000 at 12:00 AM (ET)

In linear regression the parameter estimate can be expressed as a linear combination of the dependent variables (Y's) and from that we can obtain the appropriate variance/covariance matrix.
In nonlinear regression you probably have to linearize the model at the optimal point and then use linear theory.

Your $5 contribution helps cover part the $500 annual cost of keeping this site online.