Search found 16 matches

by ManuelDewez
Tue Mar 23, 2021 5:21 pm
Forum: runmlwin user forum
Topic: DICs difference when comparing models after MCMC
Replies: 2
Views: 10148

DICs difference when comparing models after MCMC

Hello, I am comparing two models with a binary response variable with MCMC. Model 1 is a single level model, model 2 is a two level models. I understand that in this context, the DIC statistics should be used to compare models, and that the model with the lowest DIC is a better fit. Is there a value...
by ManuelDewez
Tue Mar 23, 2021 3:56 pm
Forum: runmlwin user forum
Topic: 95%Credible intervals are smaller than OR
Replies: 6
Views: 12704

Re: 95%Credible intervals are smaller than OR

That worked well, thank you Chris!
by ManuelDewez
Tue Mar 23, 2021 2:15 pm
Forum: runmlwin user forum
Topic: 95%Credible intervals are smaller than OR
Replies: 6
Views: 12704

Re: 95%Credible intervals are smaller than OR

Thank you Chris, this is the syntax I am using : runmlwin unique_dipstick_avai2cats cons private secondaryhosp paed_mother_child centered_unique_turn19_time centered_exp_capita gov VHIOOP if unique_hospital==1, level2(country2: cons) level1(id:) discrete(distribution(binomial) link(logit) denom(cons...
by ManuelDewez
Tue Mar 23, 2021 9:32 am
Forum: runmlwin user forum
Topic: 95%Credible intervals are smaller than OR
Replies: 6
Views: 12704

Re: 95%Credible intervals are smaller than OR

Hello Chris, The ACF plot shows quite some autocorrelation and the MCSE plot show that I should run the model with more iterations ( which I did) The non-ORs results look fine ( the parameters are within the 95% Credible Intervals). Gov and VHIOOP are 2 categories of the same variable. I think the i...
by ManuelDewez
Sat Mar 20, 2021 6:10 pm
Forum: runmlwin user forum
Topic: 95%Credible intervals are smaller than OR
Replies: 6
Views: 12704

95%Credible intervals are smaller than OR

Hello, I am running the following multilevel model with a binary outcome with mcmc: runmlwin unique_dipstick_avai2cats cons private secondaryhosp paed_mother_child centered_unique_turn19_time centered_exp_capita gov VHIOOP, level2(country2: cons) level1(id:) discrete(distribution(binomial) link(logi...
by ManuelDewez
Fri Mar 19, 2021 9:21 am
Forum: runmlwin user forum
Topic: Brooks-Drapers diagnostic says 1,03e+7, do I need to rerun the model with 10 300 000 iterations?
Replies: 4
Views: 10994

Re: Brooks-Drapers diagnostic says 1,03e+7, do I need to rerun the model with 10 300 000 iterations?

Hello Bill,

Thanks for your reply.

I want to report the estimate as 0.06.
Then what should I do? can I be satisfied with the 10 000 iterations of the initial model, or do I need to increase iterations, even if no up to to 10 300 000 ?

Thank you.
by ManuelDewez
Thu Mar 18, 2021 3:47 pm
Forum: runmlwin user forum
Topic: Brooks-Drapers diagnostic says 1,03e+7, do I need to rerun the model with 10 300 000 iterations?
Replies: 4
Views: 10994

Brooks-Drapers diagnostic says 1,03e+7, do I need to rerun the model with 10 300 000 iterations?

Hello, I am running the following model with MCMC for a binary outcome: runmlwin dipstick_available_for_use cons private solo centered_distance_lab99 centered_pc_turna_time3, level1(id:) discrete(distribution(binomial) link(logit) denom(cons) pql2) nopause runmlwin dipstick_available_for_use cons pr...
by ManuelDewez
Fri Mar 12, 2021 2:39 pm
Forum: runmlwin user forum
Topic: using runmlwin with survey weights
Replies: 3
Views: 10604

Re: using runmlwin with survey weights

Hello Chris,

I know that the post is from September 2020, but has there been any change on this topic, is weighting possible with MCMC in MLwin?

Thank you

Manuel
by ManuelDewez
Fri Mar 12, 2021 2:23 pm
Forum: runmlwin user forum
Topic: Coefficient legends after runmlwin
Replies: 2
Views: 9432

Re: Coefficient legends after runmlwin

Thank you George,

Is it also possible to obtain the names of the other parameters, for example the lower and upper boundaries of the 95% CI?

I am asking this because I want to create a syntax that allows including the 95% boundaries in calculations.

Thank you!