www.cmm.bristol.ac.uk/forum

Brilliant. Thanks so much for this.

Many many thanks to both of you for your thorough responses.

Indeed my data are rather extreme and this is probably what caused the convergence problems. Having checked the distribution I had zero cell counts at level 3 for several MSOAs.

For my second question, it's good to hear that using fp ...

Hi runmlwin forum.

I am having problems fitting a simple 3-level logit model using the PQL2 estimator.
I first fit the model M1 using MQL1:

runmlwin noharm cons, ///
level3(msoa01: cons) ///
level2(hhid: cons) ///
level1(subjectid: , weightvar(pw1)) ///
discrete(distribution(binomial) link ...

Thank you Chris.
For some reason it really was not possible to locate where on the computer the actual program had been installed.
It was finally resolved by re-installing MLWiN using the "Advanced" option like you suggested.

Many thanks,
Lisa

Dear runmlwin users,

I am struggling to get runlmwin to work because I am unable to specify the global path where my MLWiN programme (2.26) is installed. It seems that the location is hidden, which means that I (and IT support) can't identify a path to enter in Stata. The only paths we find are ...