Cette page appartient aux archives web de l'EPFL et n'est plus tenue à jour.
This page belongs to EPFL's web archive and is no longer updated.

Regarding a terminology

Is there any difference between a regression model and a fitted model?

Posted by Sungyeon Hong on Saturday 26 October 2013 at 13:28
Yes, there is. In the context of this course, a regression model refers to any member of the parametric class of Gaussian linear models Y = X*beta + epsilon, where epsilon follows N(0,sigma^2*I). Fitted model refers to a certain member of this class obtained by estimating the parameter beta using the maximum likelihood / least squares estimator.
Posted by Mikael Kuusela on Saturday 26 October 2013 at 18:00
Wow, thanks for your clear comment!
Posted by Sungyeon Hong on Saturday 26 October 2013 at 19:43