Small fault with convergence diagnostics graphs?

This forum is closed. You can read the posts but cannot write. We have migrated the forum to a new location where you will have to reset your password.
Forum rules
This forum is closed. You can read the posts but cannot write. We have migrated the forum to a new location (https://forum.dynare.org) where you will have to reset your password.

Small fault with convergence diagnostics graphs?

Postby reluginbuhl » Fri Jan 27, 2012 2:40 pm

I am wondering if there is a small error in the horizontal axis of the convergence diagnostics graphs. As I understand it, when I specify say 200000 replications per chain, and a burnin of 40%, Dynare should take a posterior sample of (1 - 40%) of 200000 = 120000 replications per chain. I have noticed, however, that the convergence diagnostic graphs produce a horizontal axis which runs to 200000 instead of 120000. I thought the burnin part of the chain was left out of the calculation of these diagnostics. Is that correct? Shouldn't the axis only go to 120000 in this case?

Thank you.

Sincerely,
Rob Luginbuhl
reluginbuhl
 
Posts: 53
Joined: Wed Mar 04, 2009 2:41 pm

Return to Dynare help

Who is online

Users browsing this forum: Google [Bot] and 9 guests