MCMC residuals

Welcome to the forum for MLwiN users. Feel free to post your question about MLwiN software here. The Centre for Multilevel Modelling take no responsibility for the accuracy of these posts, we are unable to monitor them closely. Do go ahead and post your question and thank you in advance if you find the time to post any answers!

Remember to check out our extensive software FAQs which may answer your question: ... port-faqs/
Post Reply
Posts: 18
Joined: Fri Feb 04, 2011 12:46 pm

MCMC residuals

Post by ewancarr »

Hi all,

I'm estimating a two-level logistic regression model, with MCMC estimation. Previously, I've used IGLS estimation, and have used "Model >> Residuals" to plot the ranked residuals for each level-2 unit (the typical 'caterpillar plot').

I notice in the MCMC manual (Browne, 2009) that there are instructions to calculate residuals specifically for MCMC estimation (p. 51). My question is then:
  • Is the 'old' method of calculating residuals (using "Models >> Residuals") therefore invalid for MCMC estimation?
The above reference seems to imply that the new method is more accurate. An alternative question, therefore:
  • Are MCMC residuals calculated using "Model >> Residuals" sufficiently accurate in order to produce these caterpillar plots?
Any help at all would be much appreciated!

CCSR, University of Manchester
Post Reply