Search found 12 matches

by scarpent
Fri May 08, 2015 12:00 pm
Forum: runmlwin user forum
Topic: multinomial event history model
Replies: 1
Views: 3685

multinomial event history model

Hi,

I try to run a discrete-time multinomial event history model with four exit states (work, active labour market participation, social security benefit entitlement and other) for 13,552 social assistance beneficiaries for their repeated spells in social assistance. I have a stepwise ...
by scarpent
Wed Feb 19, 2014 3:46 pm
Forum: runmlwin user forum
Topic: citing MLwiN 2.29
Replies: 2
Views: 4814

Re: citing MLwiN 2.29

Thank you, George

Kind regards,

Sarah
by scarpent
Wed Feb 19, 2014 2:25 pm
Forum: runmlwin user forum
Topic: citing MLwiN 2.29
Replies: 2
Views: 4814

citing MLwiN 2.29

Hi,

I wonder how using MLwiN 2.29 for MCMC estimation with the runmlwin module for Stata should be exactly cited.

On the website of the University of Bristol (http://www.bristol.ac.uk/cmm/software/mlwin/refs.html) I find the following information on citing MLwiN:

MLwiN Version 2.1

Rasbash, J ...
by scarpent
Wed Feb 05, 2014 3:07 pm
Forum: runmlwin user forum
Topic: correlated random effects
Replies: 2
Views: 4630

Re: correlated random effects

Thank you for this information, George
by scarpent
Wed Feb 05, 2014 11:07 am
Forum: runmlwin user forum
Topic: correlated random effects
Replies: 2
Views: 4630

correlated random effects

Hi,

I fitted a discrete-time multilevel event history model to estimate the probability of leaving social assistance.
Beneficiaries are cross-nested in welfare agencies.
I use MCMC estimation with IGLS estimation for the nested model as priors.

In the current model the random effects at ...
by scarpent
Thu Oct 17, 2013 2:51 pm
Forum: runmlwin user forum
Topic: Gibbs or Metropolis Hastings sampling
Replies: 6
Views: 11514

Re: Gibbs or Metropolis Hastings sampling

Thanks, George

I found indeed the Advanced MCMC Methodology Options in the saved worksheet.

Best wishes,

Sarah
by scarpent
Tue Oct 15, 2013 9:36 am
Forum: runmlwin user forum
Topic: Gibbs or Metropolis Hastings sampling
Replies: 6
Views: 11514

Gibbs or Metropolis Hastings sampling

Dear George and Chris,

I am running a discrete-time event history model with logit link function to estimate the probability of leaving social assistance.
I have 160624 person-months nested within individuals and cross-classified in 574 welfare agencies.
I use MCMC estimation with IGLS ...
by scarpent
Tue Jan 22, 2013 10:48 am
Forum: runmlwin user forum
Topic: error message - multinomial logit model
Replies: 4
Views: 7579

Re: error message - multinomial logit model

Hi George and Chris,

Thank you for your comments and suggestions!

The IGLS-model gives the MLwiN error message.

I found out that I have indeed a convergence problem, even with the empty model. It seems to be a problem of non-identification of a dependent competing risks model.
However, the ...
by scarpent
Thu Jan 17, 2013 2:23 pm
Forum: runmlwin user forum
Topic: error message - multinomial logit model
Replies: 4
Views: 7579

error message - multinomial logit model

Hi,

I try to run a multinomial logit discrete-time event history analysis with Mlwin 2.26, but I get the error message 'group 18 contains no columns(calc)'.
I examine the determinants of exit from welfare to three mutually exclusive states (work, work with supplementary welfare benefit, other ...
by scarpent
Fri Apr 20, 2012 3:26 pm
Forum: runmlwin user forum
Topic: discrete time multilevel event history model
Replies: 5
Views: 9843

Re: discrete time multilevel event history model

Hi,

Thank you for the suggestions.
After updating stata I still receive an error message:
setup_problem(): 3499 strtoreal() not found
put(): - function returned error
<istmt>: - function returned error
But with the prefix version 10: it works.

Thanks a lot!

Best wishes,

Sarah