Search found 31 matches

by rdmcdowell
Tue Oct 31, 2017 10:32 am
Forum: MLwiN user forum
Topic: Mlwin supplement: autocorrelated errors in continuous time
Replies: 2
Views: 2747

Re: Mlwin supplement: autocorrelated errors in continuous time

Thanks very much for clarifying this and pointing me in the right direction. Is it the case that the multivariate approach only works for Bernoulli responses (ie 0 or 1) rather than grouped binomial data (eg 3 successes out of 7 trials) in Mlwin?
by rdmcdowell
Thu Oct 26, 2017 9:59 am
Forum: MLwiN user forum
Topic: dynamic autoregressive models
Replies: 0
Views: 2466

dynamic autoregressive models

Hello. I see from the Lemma course on multilevel modelling of repeated measures (Ch 15) that Model 3 (where u`j' is a factor with loading 1 for time 1 and freely estimated for other time-points) cannot be estimated in Mlwin. I wondered if with the new release of Mlwin whether this is still the case....
by rdmcdowell
Tue Oct 24, 2017 1:53 pm
Forum: MLwiN user forum
Topic: Mlwin supplement: autocorrelated errors in continuous time
Replies: 2
Views: 2747

Mlwin supplement: autocorrelated errors in continuous time

Hello. I am hoping someone will be able to clarify a point on this for me. I see from the Mlwin supplement, when fitting a multilevel/longitudinal model to an outcome which is being treated as continuous, it is possible to estimate both between subject/within subject variances, and additionally allo...
by rdmcdowell
Tue Sep 05, 2017 1:59 pm
Forum: MLwiN user forum
Topic: Informative priors
Replies: 5
Views: 4207

Re: Informative priors

Hi Bill Yes, all the materials available for Mlwin/Runmlwin are excellent and extremely informative. You are absolutely correct when you say that most clusters are either 0 or 1. I was able to run the analyses on collapsed (2 level) data without any problems in estimation due to the large size of th...
by rdmcdowell
Mon Sep 04, 2017 11:14 am
Forum: MLwiN user forum
Topic: Informative priors
Replies: 5
Views: 4207

Re: Informative priors

Hello Bill Thanks for your response and for that helpful citation. What I mean that the estimates I am obtaining using MCMC estimation in no way correspond to those obtained using IGLS. Consider a simple example of a logistic model with a random intercept only. Using IGLS estimation I may get an est...
by rdmcdowell
Fri Sep 01, 2017 2:44 pm
Forum: MLwiN user forum
Topic: Informative priors
Replies: 5
Views: 4207

Informative priors

Hello. I would be interested to read others' thoughts on this matter. I am fitting a multilevel cross classified model using Mcmc estimation in mlwin. I've found that the various non-informative priors found do not work well, so I am leaning towards informative priors. I probably will only be using ...
by rdmcdowell
Fri Sep 01, 2017 2:29 pm
Forum: runmlwin user forum
Topic: Error message: too many macros
Replies: 10
Views: 14584

Re: Error message: too many macros

Thank very much for this response. At least I'm reassured now on the correct procedure if I wish to go down this route. Thanks
by rdmcdowell
Thu Aug 31, 2017 7:26 am
Forum: runmlwin user forum
Topic: Advice on cross-classified models with large data sets
Replies: 11
Views: 7648

Re: Advice on cross-classified models with large data sets

Thank you for your responses and updated code. I have been able to get my cross-classified multilevel models working now using MlwIn. It really has been a tremendously useful tool.
by rdmcdowell
Wed Aug 30, 2017 3:16 pm
Forum: runmlwin user forum
Topic: Advice on cross-classified models with large data sets
Replies: 11
Views: 7648

Re: Advice on cross-classified models with large data sets

Thanks! I restarted Stata and everything seems to be working well now, which is great! On a slight aside, I see from the MCMC manual you can export code to Winbugs if you wish to tweak the priors from the available options. Does this mean then that the revised code has to be run in winbugs and can't...
by rdmcdowell
Wed Aug 30, 2017 1:38 pm
Forum: runmlwin user forum
Topic: Advice on cross-classified models with large data sets
Replies: 11
Views: 7648

Re: Advice on cross-classified models with large data sets

Thanks for that very prompt response! I downloaded that version of runmlwin and installed it, though same came up with the same issue. As it stands the last column in my matrix of priors is called OD:bcons_1. I've tried renaming it to RP1:var(bcons_1) and RP1:var(cons) but am still getting the error...