Re: st: question about sample selection and hierarchical linear modelling

[Jeph Herrin <junk@spandrel.net>]

To estimate the model, you can try:

 xtmixed rating demo1 || respondentID:

where -rating- contains your rating, -demo1- is your demographic
variable, and respondent ID identifies the respondent. I use
only one demographic variable, because with only 10 respondents
that's probably the max you'll want to include.

I'm not sure how or even if you can examine sample selection bias
unless you have some exogenous variable in mind.

Hope this helps,
Jeph


Ed Levitas wrote:
> Statalisters,
>
> We are trying to estimate a hierarchical linear model with 2 levels.
> The data might be subject to sample selection bias.  Specifically,
> please assume the following:
>
> We give 10 respondents a description of 20 different scenarios (i.e.,
> respondent 1 receives a description of the 20 different scenarios,
> respondent 2 receives the same descriptions of the 20 different
> scenarios etc).  Respondents have to rate the feasibility of each of the
> 20 scenarios.  There rating is an outcome variable and based on the
> descriptions give, we have produced predictor variables.  We also have
> demongraphic data on the respondents that does not vary across them.  As
> such we have 10 observations at the fixed (or respondent) level and 200
> observations at the random (or scenario) level.  We need to assess the
> possibility of sample selection bias in our HLM since our 10 respondents
> are drawn from a population where many of the members did not have the
> experience necessary to engage in our survey.
>
> Can anyone suggest ways/citations that might help us estimate in STATA
> this HLM model with (possible) sample selection bias?
>
> Thanks in advance.
> Ed
>
> ****************************************
> Edward Levitas, PhD
> Associate Professor
> Sheldon B. Lubar School of Business 
> University of Wisconsin-Milwaukee
> 3202 N. Maryland Ave.
> Milwaukee, WI  53211
> ph: (414) 229-6825
> fx: (414) 229-6957
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/