Re: st: Standard deviation of the error term in asclogit

[Maarten Buis <maartenlbuis@gmail.com>]

On Thu, Sep 8, 2011 at 3:04 PM, esther adler wrote:
> My issue is that I have reasons to believe my individuals have different standard errors for their error term; by this I mean that some are more "accurate" than others in their choice. Is there a way I can get Stata to take account of this?
>
> Also, since I have variables that I suppose may explain how accurate the individual is in her choices (for example, mathematical proficiency and education), is there a way to get the std error or the error term to depend on this?

I suppose you mean standard deviation of the error term rather than
standard error of the error term.

The problem with such heterogeneous choice models is that they tend to
be hopelessly sensitive to getting the functional form of _every_ part
of your model correct. Any deviation in the probability part of the
model influences the residuals, and the model for the residuals
influence the parameter estimates in the main probability part of the
model. So any error in your model tends to propagate to all other
parts of your model. So I do not think that that is a very promising
avenue to pursue.

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany


http://www.maartenbuis.nl
--------------------------
*
*   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/