Dear Stata-list,
I am estimating a growth curve model based on unbalanced panel-data with 6 waves of data. The dependent variable is victimization, and age is the sole predictor variable. There are 17 different age cohorts and models are estimated for each age cohort separately.
Some information about the data: the victimization variable counts the number of victimization events and is highly skewed with about 96-98% being zero, 1-3% being one, and less than 1% being 2 till 9. Every cohort contains around 1000 persons. I would like the model to contain a random intercept and random slope.
When I estimate a linear model using -xtmixed-, the results seem logical and consistent, but since the dependent variable is a count and contains many zero's, I also estimated poisson and logit models. The code I used is as follows (id being the unique identifier for a person):
xtmepoisson victimization_count age || id: age, cov(unstr) mle variance
xtmelogit victimization_dich age || id: age, cov(unstr) mle variance
For the poisson model I get highly illogical and inconsistent results, and for most age cohorts I get error messages such as 'flat or discontinuous region encountered', 'discontinuous region with missing values encountered', 'initial values not feasible' and 'Hessian has become unstable or asymmetric'.
For the logit model I get the same error message for each age cohort: 'initial values not feasible'.
Does anyone know what is going on and if there are any solutions? Any suggestions are more than welcome.
Many thanks,
Margit Averdijk
_________________________________________________________________
Connect and share in new ways with Windows Live.
http://www.windowslive.com/share.html?ocid=TXT_TAGHM_Wave2_sharelife_012008
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
