Search found 1335 matches

by ChrisCharlton
Wed Jan 24, 2024 10:08 am
Forum: MLwiN user forum
Topic: Problem with import start parsing
Replies: 3
Views: 301

Re: Problem with import start parsing

MLwiN version 2.01 is almost 20 years old, predating Realcom-Impute, and therefore doesn't have the facilities to load imputed datasets created by this. I suggest updating to the most recent version via the form at https://www.cmm.bristol.ac.uk/clients/softwaredownload/ and checking whether you get ...
by ChrisCharlton
Tue Jan 23, 2024 1:39 pm
Forum: MLwiN user forum
Topic: Problem with import start parsing
Replies: 3
Views: 301

Re: Problem with import start parsing

Could you please provide the MLwiN version number that you are running, as well as the steps taken up to the point of the crash?
by ChrisCharlton
Tue Jan 23, 2024 1:35 pm
Forum: R2MLwiN user forum
Topic: mlwinfitMCMC object fitted values (propensity scores) storage
Replies: 1
Views: 186

Re: mlwinfitMCMC object fitted values (propensity scores) storage

You should be able to do this with the overloads that R2MLwiN provides for the generic predict ( https://stat.ethz.ch/R-manual/R-devel/library/stats/html/predict.html ) function. To find more information on the syntax supported in R2MLwiN run: help("predict.mlwinfitIGLS") or: help("pr...
by ChrisCharlton
Mon Jan 22, 2024 3:12 pm
Forum: R2MLwiN user forum
Topic: Binary outcome Multiple membership model
Replies: 5
Views: 695

Re: Binary outcome Multiple membership model

Are you checking the data from with R or MLwiN? I would suggest turning on debugmode=TRUE again and then browsing the data as it is in MLwiN via the Data window, as it's possible that it isn't being sent correctly from R to MLwiN. The message that you're seeing is only triggered if the software come...
by ChrisCharlton
Wed Jan 10, 2024 9:27 am
Forum: R2MLwiN user forum
Topic: Binary outcome Multiple membership model
Replies: 5
Views: 695

Re: Binary outcome Multiple membership model

Thanks for this additional information. Unfortunately MLwiN does not support fitting multiple membership models with (R)IGLS, other than using the constraint tricks detailed in chapter 19 of the MLwiN User's Guide which are not supported in R2MLwiN. When specifying discrete response models in R2MLwi...
by ChrisCharlton
Wed Jan 03, 2024 8:34 pm
Forum: R2MLwiN user forum
Topic: Bivariate Logistic Distribution
Replies: 8
Views: 695

Re: Bivariate Logistic Distribution

I forgot to also mention that for MCMC multivariate models in MLwiN the only link function you can use for a binomial response is probit. This is because it fits the response as a latent variable in a multivariate normal model (see Bayesian analysis of Binary and Polychotomous Response Data ). You s...
by ChrisCharlton
Wed Jan 03, 2024 4:26 pm
Forum: Stat-JR user forum
Topic: 3-level dataset using STAT-JR
Replies: 2
Views: 540

Re: 3-level dataset using STAT-JR

You can find information about support for missing data in Stat-JR on the following page:

Imputation for Multilevel Models with Missing Data Using Stat-JR
by ChrisCharlton
Wed Jan 03, 2024 12:30 pm
Forum: Realcom user forum
Topic: STATA 18
Replies: 1
Views: 648

Re: STATA 18

If you are still encountering this problem could you please provide examples of syntax that worked previously and is now causing problems?
by ChrisCharlton
Wed Jan 03, 2024 12:28 pm
Forum: R2MLwiN user forum
Topic: Bivariate Logistic Distribution
Replies: 8
Views: 695

Re: Bivariate Logistic Distribution

To answer the first question, you can model bivariate logistic models with R2MLwiN. To do this you would add the following option to your model specification " D = c("Mixed", "Binomial", "Binomial") ". For an example of this in the context of a model see the l...
by ChrisCharlton
Fri Dec 08, 2023 11:19 am
Forum: runmlwin user forum
Topic: Runmlwin Wrong Parameters
Replies: 3
Views: 730

Re: Runmlwin Wrong Parameters

Could you please try adding the viewfullmacro option to your runmlwin command and post the MLwiN script that this generates?