Search found 1134 matches

by ChrisCharlton
Wed Feb 12, 2020 10:19 am
Forum: MLwiN user forum
Topic: problem with install
Replies: 1
Views: 214

Re: problem with install

Can you provide some details regarding what the error messages say?
by ChrisCharlton
Fri Jan 31, 2020 11:16 am
Forum: MLwiN user forum
Topic: MlWin on Mac
Replies: 1
Views: 195

Re: MlWin on Mac

The native Mac version of MLwiN (mlnscript) is a script only version, so you will probably want to run it either via R with R2MLwiN ( http://www.bristol.ac.uk/cmm/software/r2mlwin/ ) or Stata with runmlwin ( http://www.bristol.ac.uk/cmm/software/runmlwin/ ). One thing to watch out for is that you ne...
by ChrisCharlton
Thu Jan 30, 2020 12:17 pm
Forum: runmlwin user forum
Topic: using runmlwin in batch mode on Unix
Replies: 19
Views: 1166

Re: using runmlwin in batch mode on Unix

Could you please try replacing your version of the file "runmlwin.ado" with the development version from:

https://bitbucket.org/cmm_stata/runmlwin/src/master/

and let me know if that fixes the problem?
by ChrisCharlton
Wed Jan 08, 2020 10:14 am
Forum: MLwiN user forum
Topic: Basic question about Multilevel Analysis and MlWiN: Group vs. grand mean centering
Replies: 1
Views: 121

Re: Basic question about Multilevel Analysis and MlWiN: Group vs. grand mean centering

You may find the following explanation from Kelvyn Jones, one of our colleagues, useful as it provide an overview along with some links for further reading:

https://www.researchgate.net/post/MLM_A ... _centering
by ChrisCharlton
Tue Jan 07, 2020 10:58 am
Forum: runmlwin user forum
Topic: VPC in a three level random slopes model
Replies: 1
Views: 83

Re: VPC in a three level random slopes model

See viewtopic.php?f=3&t=815 for a previous discussion on this topic.
by ChrisCharlton
Tue Jan 07, 2020 10:39 am
Forum: runmlwin user forum
Topic: Error: "last estimates not found"
Replies: 1
Views: 75

Re: Error: "last estimates not found"

The lroc command requires estimates from the logistic, logit, probit and ivprobit command, as described in the help for this command (https://www.stata.com/help.cgi?lroc). Unfortunately this means that it cannot use the estimates from the runmlwin command.
by ChrisCharlton
Tue Jan 07, 2020 10:30 am
Forum: runmlwin user forum
Topic: obtaining level 2 residuals from multilevel ordinal model
Replies: 2
Views: 119

Re: obtaining level 2 residuals from multilevel ordinal model

This works for me if I do the equivalent of the following: * Fit model using IGLS MQL1 runmlwin hiv cons, /// level2(group: (cons, contrast(1/2))) /// level1(idcode:) /// discrete(dist(multinomial) link(ologit) denom(cons) basecategory(0)) /// nopause * Fit model using MCMC runmlwin hiv cons, /// le...
by ChrisCharlton
Tue Dec 10, 2019 4:12 pm
Forum: MLwiN user forum
Topic: Recoding new sequence variable from continuous time variable
Replies: 4
Views: 259

Re: Recoding new sequence variable from continuous time variable

Did you set subjid as the variable under "On blocks defined by"? Doing this should restart the sequence back to one each time the value in this column changes.
by ChrisCharlton
Tue Dec 10, 2019 3:33 pm
Forum: MLwiN user forum
Topic: Recoding new sequence variable from continuous time variable
Replies: 4
Views: 259

Re: Recoding new sequence variable from continuous time variable

I think that the following may do what you want: Sort your data by visdy within subjid . You can do this either via the Data Manipulation->Sort menu or via the SORT command. Note that this will only reorder the selected columns, so you need to include all the columns representing your data here. Gen...
by ChrisCharlton
Fri Dec 06, 2019 10:49 am
Forum: MLwiN user forum
Topic: multinomial logistic regression - Error design vector length - no missings
Replies: 11
Views: 6276

Re: multinomial logistic regression - Error design vector length - no missings

It is hard to determine what is going on here, especially without seeing the data, however it may be related to around half the data being in one of the categories (NRM Only). Because of this there may be groups where all of the records are in this category. If MQL1 works and PQL2 doesn't then I wou...