Search found 1359 matches

by ChrisCharlton
Mon Jun 18, 2012 4:36 pm
Forum: runmlwin user forum
Topic: Error fitting Multinomial logit using PQL2
Replies: 6
Views: 10496

Re: Error fitting Multinomial logit using PQL2

I would suggest running the command again, but without the nopause option so that you can check what's in the equations window. It's possible that one or more of the results have gone to an invalid number, such as infinity.
by ChrisCharlton
Mon Jun 18, 2012 4:31 pm
Forum: MLwiN user forum
Topic: Not enough work space
Replies: 4
Views: 9184

Re: Not enough work space

Increasing the worksheet size would normally be the solution to this message. What size did you increase it to?
by ChrisCharlton
Thu Jun 14, 2012 2:54 am
Forum: MLwiN user forum
Topic: help check codes for two-level model with sampling weights
Replies: 1
Views: 5003

Re: help check codes for two-level model with sampling weigh

Any model that worked with version 2.02, which from the screen shot appears to be the version that you were using, should still work with the most recent version. If you wanted to double check this you can download a 30-day trial version from:

http://www.bris.ac.uk/cmm/software/mlwin/download/
by ChrisCharlton
Tue Jun 05, 2012 3:54 pm
Forum: MLwiN user forum
Topic: error term
Replies: 1
Views: 4954

Re: error term

I'm not sure what is causing this, but it may be that it is running out of worksheet space. I suggest that you try increasing the allocated worksheet size and see whether you get the same issue.
by ChrisCharlton
Tue Jun 05, 2012 3:49 pm
Forum: MLwiN user forum
Topic: Install problem
Replies: 1
Views: 4504

Re: Install problem

Are you trying to install it with an account with administrative privileges? In order to start the trial the application needs to write to system areas when it is installed. Once you have installed the application as an administrator you should be able to run it as a standard user.
by ChrisCharlton
Tue May 22, 2012 10:11 pm
Forum: MLwiN user forum
Topic: Building macros on the fly?
Replies: 1
Views: 4544

Re: Building macros on the fly?

We have recently been trying to make sure that everything in the graphical interface has a command equivalent, so if you spot anything that should do but doesn't please let us know. To see the macro commands as they are generated you can open the Data Manipulation->Command Interface window and ...
by ChrisCharlton
Thu May 17, 2012 4:07 pm
Forum: MLwiN user forum
Topic: Four level problem
Replies: 2
Views: 6492

Re: Four level problem

In case anyone else comes across this problem: It appears that there is a bug in MLwiN where it has problems generating estimates if some of the higher level units contain no observations after taking into account missing data. The workaround for this is to omit any records where a predictor has a ...
by ChrisCharlton
Mon May 14, 2012 2:36 pm
Forum: MLwiN user forum
Topic: Four level problem
Replies: 2
Views: 6492

Re: Four level problem

We are not sure why you are experiencing crashes with your original model, however if you can send an example worksheet with instructions on how to reproduce the crash we will look into it.
by ChrisCharlton
Thu May 03, 2012 11:36 am
Forum: runmlwin user forum
Topic: Problem getting residuals: after merge, not all observations
Replies: 10
Views: 20487

Re: Problem getting residuals: after merge, not all observat

I've just tested this with the tutorial dataset by recoding some of the schools, and you're right. I get the following message before it tries to fit the model:

The data must be sorted according to the order of the model hierarchy: school student.

So I guess that eliminates that as a possible ...
by ChrisCharlton
Thu May 03, 2012 8:35 am
Forum: runmlwin user forum
Topic: Problem getting residuals: after merge, not all observations
Replies: 10
Views: 20487

Re: Problem getting residuals: after merge, not all observat

MLwiN calculated residuals in a short form with one row per level 2 unit, i.e.

countid|residual
-------+---------
1 | 0.2
2 | 0.3

we then merge this back into the original data (if I remember correctly using the level identifier).

If your level identifier isn't unique for each unit of that ...