Search found 424 matches

by GeorgeLeckie
Tue Aug 02, 2016 11:43 am
Forum: MLwiN user forum
Topic: Data set up Longitudinal Multiple Membership Model
Replies: 11
Views: 7071

Re: Data set up Longitudinal Multiple Membership Model

Hi Gerine, There is a lot of information here. However, as far as I can see your scores are the level-1 units in cross-classified data structure rather than a multiple membership structure. You have a separate score for each child in each wave. So each score is associated with one child, one class a...
by GeorgeLeckie
Tue Aug 02, 2016 11:30 am
Forum: runmlwin user forum
Topic: Predicted Probability for ML Ordinal Model
Replies: 3
Views: 1528

Re: Predicted Probability for ML Ordinal Model

Hi Vivian, Yes. What you have done should work. Please can you send through more details about the MLwiN crash. Alternatively, the more "runmlwin" approach would be to calculate these predicted probabilities in Stata. See http://www.bristol.ac.uk/cmm/media/runmlwin/11_Fitting_an_Ordered_Category_Res...
by GeorgeLeckie
Fri May 20, 2016 4:02 pm
Forum: runmlwin user forum
Topic: Question VPC calculation
Replies: 1
Views: 842

Re: Question VPC calculation

Dear Mahadev11,

Suggest you calculate VPCs based on the latent response formulation of the logistic regression model. See Module 7 of the LEMMA online course (Section 7.2) or any decent multilevel textbook for details.

Best wishes

George
by GeorgeLeckie
Tue May 03, 2016 3:50 pm
Forum: runmlwin user forum
Topic: Random effects prediction and interpretation in multilevel logit models
Replies: 2
Views: 1112

Re: Random effects prediction and interpretation in multilevel logit models

Dear rahulvbb,

The predicted state random effects measure how much higher the predicted log-odds are in each state relative to the average state.

Researchers often plot these in a caterpillar plot to aide graphical interpretation. You can do this using the -serrbar- command.

Best wishes

George
by GeorgeLeckie
Wed Apr 13, 2016 3:03 pm
Forum: runmlwin user forum
Topic: 2-level Poisson model - MQL1 works fine, PQL2 crashes
Replies: 2
Views: 1300

Re: 2-level Poisson model - MQL1 works fine, PQL2 crashes

Hi Nils, Your DGP and runmlwin syntax all look fine. The problem appears to be with some particularly high counts generated by your DGP. Essentially if you specify a lower true value for your level-2 variance everything is fine, but as you pump up the level-2 variance you get more and more extreme c...
by GeorgeLeckie
Wed Apr 13, 2016 2:40 pm
Forum: runmlwin user forum
Topic: Random Coefficient Model: Zero Variance/Covariance Terms
Replies: 1
Views: 1205

Re: Random Coefficient Model: Zero Variance/Covariance Terms

Dear Jack, Given a binary response, the model looks rather complex with many random coefficients. A binary response contains far less information than a continuous response. Also your cluster sizes are small with 8 pupils per school on average. There will be little variation in the response within c...
by GeorgeLeckie
Wed Apr 13, 2016 2:32 pm
Forum: runmlwin user forum
Topic: Variance estimates
Replies: 1
Views: 1014

Re: Variance estimates

Dear Francisca, An estimate of zero for the level-4 variance looks a bit strange. You don't appear to have done anything obviously wrong in terms of your runmlwin syntax so the answer probably lies with your data. It would be worth trying to fit the model by MQL1, MQL2, PQL1 and especially MCMC to c...
by GeorgeLeckie
Wed Apr 13, 2016 2:28 pm
Forum: runmlwin user forum
Topic: Predicted probabilties for multivariate logistic multilevl model
Replies: 1
Views: 973

Re: Predicted probabilties for multivariate logistic multilevl model

Dear francescomolteni , I'm afraid there is no automated way to do this. You will have to do the calculations by hand from first principles. Module 7 of the lemma training materials and in particular the accompanying runmlwin do-files may be of some help. See for example section 7.5 http://www.brist...
by GeorgeLeckie
Wed Apr 13, 2016 2:24 pm
Forum: runmlwin user forum
Topic: Question VPC calculation
Replies: 1
Views: 819

Re: Question VPC calculation

Hi Mahadev11, The easiest approach would be to use the latent response method. Any good multilevel text book will describe this. You could also look at our free online course Module 7: Multilevel Models for Binary Responses STATA Practical (p.18) Essentially you calculate the VPC statistics in the u...
by GeorgeLeckie
Tue Mar 08, 2016 4:31 pm
Forum: MLwiN user forum
Topic: negative binomial regression. How to set up the Wald test to compare models?
Replies: 2
Views: 1496

Re: negative binomial regression. How to set up the Wald test to compare models?

Dear csswader2 , Suppose you want to perform a Wald test of the current model against a simpler version where you omit the last two covariates in your model, fatalism and informult. This is equivalent to testing the null hypothesis that both coefficients are jointly equal to zero H0: \beta_9 = 0 & \...