Search found 1341 matches
- Wed Jan 04, 2012 10:26 am
- Forum: MLwiN user forum
- Topic: Obtaining and graphing predicted probabilities in Mlwin
- Replies: 2
- Views: 7004
Re: Obtaining and graphing predicted probabilities in Mlwin
There are some examples in section 4.2 of the User Guide (http://www.bristol.ac.uk/cmm/software/m ... man-09.pdf) and section 2 of the Manual Supplement (http://www.bristol.ac.uk/cmm/software/m ... 0-supp.pdf) that you might find useful.
- Wed Jan 04, 2012 10:09 am
- Forum: MLwiN user forum
- Topic: Wrong parameters(SETX)
- Replies: 2
- Views: 7324
Re: Wrong parameters(SETX)
As you have 158 origins I think that the command should be: SETX 'CONSTANT' 3 'ORIGIN' C101-C 2 58 C50 If this still doesn't work could you confirm that the example on page 276 of the MLwiN user guide works for you. If it does then could you email me an example worksheet that demonstrates the proble...
- Tue Nov 22, 2011 5:24 pm
- Forum: runmlwin user forum
- Topic: Log likelihood and deviance not displayed
- Replies: 5
- Views: 7724
Re: Log likelihood and deviance not displayed
We have added a warning message for when the likelihood is missing. This will appear in the next release of runmlwin. If you could still send us an example of this we will be able to test that this works.
- Thu Nov 17, 2011 11:22 am
- Forum: MLwiN user forum
- Topic: 0 of 0 cases in use - equation
- Replies: 2
- Views: 6383
Re: 0 of 0 cases in use - equation
Columns in an MLwiN worksheet do not all have to be of the same length, only those used in the model. Because of this MLwiN does not know how many cases you are using until you have set up your model to a sufficient degree to be able to determine this. If you set up your model you should see the cas...
- Mon Nov 14, 2011 4:33 pm
- Forum: runmlwin user forum
- Topic: Error message regarding level 1 ID variable - Obsno is held
- Replies: 8
- Views: 11223
Re: Error message regarding level 1 ID variable - Obsno is h
I would just add that you may find the mcmcsum command that accompanies runmlwin useful for performing diagnostics on your MCMC runs.
- Thu Oct 27, 2011 3:23 pm
- Forum: runmlwin user forum
- Topic: Error message regarding level 1 ID variable - Obsno is held
- Replies: 8
- Views: 11223
Re: Error message regarding level 1 ID variable - Obsno is h
Would it be possible to email me the syntax and data so that I can attempt to replicate this and determine whether the problem is in runmlwin or MLwiN?
- Wed Oct 26, 2011 1:53 pm
- Forum: runmlwin user forum
- Topic: Error message: Could not load plugin
- Replies: 12
- Views: 18499
Re: Error message: Could not load plugin
I'm glad that you have now managed to get it working to some degree. The MCMC diagnostic plugin is also used when reporting the model results to calculate statistics such as the ESS from the parameter chains. There is a nodiagnostics option which prevents these from being calculated and instead uses...
- Wed Oct 26, 2011 12:09 pm
- Forum: runmlwin user forum
- Topic: Error message: Could not load plugin
- Replies: 12
- Views: 18499
Re: Error message: Could not load plugin
That should be the only other place that plugin is used. Is it possible that you have forgotten to run the discard command after editing the ado file, to make Stata reload it with your changes?
- Wed Oct 26, 2011 11:16 am
- Forum: runmlwin user forum
- Topic: Error message: Could not load plugin
- Replies: 12
- Views: 18499
Re: Error message: Could not load plugin
You can work around this second plugin issue by replacing all references of runmlwin_quietshell with shell . This will however mean that runmlwin can't be run in Stata batch mode. The final plugin that might cause an issue is the MCMC diagnostics plugin. Unfortunately there is currently no workaroun...
- Wed Oct 26, 2011 9:24 am
- Forum: runmlwin user forum
- Topic: Error message: Could not load plugin
- Replies: 12
- Views: 18499
Re: Error message: Could not load plugin
I am still not sure what is causing this as we have run this on a similar setup without issues. It possible that it can't find the correct C runtime library. We should be using the one that comes with Stata, however if not you could install this from http://www.microsoft.com/download/en/details.aspx...