--- Jeremy Cheesman wrote:
> I am attempting to evaluate mean / median WTP and confidence intervals for a
> contingent valuation survey using the payment card approach. This approach
> presents a survey respondent with a range of prices for some good and asks
> them to identify the highest price they would be willing to pay for the
> good. It is assumed that the respondent's true willingness to pay is bounded
> at the lower end by the amount they said they would pay and at the higher
> end by the next highest amount presented to the respondent (that they
> indicated they would not pay). Where the respondent indicates they would pay
> the highest price presented their WTP is unbounded (unbounded upper
> responses account for less than 3 percent of our survey respondents).
>
> I am wondering if anyone has 'canned' parametric and / or non-parametric
> models to estimate these models or whether there are any guidelines for
> constructing these models in STATA? For the parametric models I would like
> to evaluate normal and log-normal distributions, possibily truncating the
> normal distribution to allow for only non-negative WTP.
see -help intreg- (note that an estimate of the mean is the constant in a
regression without explanatory variables)
Hope this helps,
Maarten
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
*
* 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/
