Different software, different results

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: http://www.bristol.ac.uk/cmm/software/s ... port-faqs/
Post Reply
laureannegille
Posts: 1
Joined: Tue Sep 12, 2017 12:21 pm

Different software, different results

Post by laureannegille » Tue Sep 12, 2017 1:00 pm

Hello,

using the same database but different software, I get different results and was wondering where it can come from

My model is very simple : 2 levels, dependantvariable_ij = \beta0 + \beta1 x Metric + u_0j + e_ij

Here are the results I get :
Capture.PNG
Capture.PNG (32.73 KiB) Viewed 22 times
As you can see, R and Matlab provide similar results contrary to MLwiN.
I have checked that the depending variable is well defined in all cases and that I use the same computation method (RIGLS in MLwin is the same as reml in Matlab according to the help documentation).

Do you think at any other source of getting such different results, even in their interpretation ?
Thank you for any advice you can provide

ChrisCharlton
Posts: 870
Joined: Mon Oct 19, 2009 10:34 am

Re: Different software, different results

Post by ChrisCharlton » Tue Sep 12, 2017 3:56 pm

We cannot see an obvious reason for this difference. Do you have an example worksheet that you would be able to share that exhibits this behaviour?

Post Reply