Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: not quite double bounded CV


From   "Mentzakis, Emmanouil" <e.mentzakis@abdn.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: not quite double bounded CV
Date   Sat, 24 May 2008 12:45:39 +0100

Coba,

 

An interval regression model is often used where the bids used are entered as an independent variable. 

Have a look at the Hanneman (1991) paper. Essentially your format is a variation of the double bounded dichotomous choice where rather than four outcomes you have three. The purpose of this is to take account of some biases often found in DBDC.

 

Modifying the likelihood proposed in the Hanneman paper will do. If you want normal distribution you can use -intreg-. Otherwise you can program your own with -ml-. Have a look at the Statalist archives, probably you can find something there.


Cheers

Manos

 

Hanneman, M., Loomis, J. and Kanninen, B. 1991. Statistical Efficiency of Double Bounded Dichotomous Contingent Choice Contingent Valuation, American Journal of Agricultural Economics, 73:1255-1263.


________________________________

From: owner-statalist@hsphsun2.harvard.edu on behalf of Jacoba van der Gaag
Sent: Sat 5/24/2008 7:46 AM
To: statalist@hsphsun2.harvard.edu
Subject: st: not quite double bounded CV



Hi,

I have a survey on willingness to pay for health insurance that takes
the following form: respondents are first asked if they are willing to
pay an Amount A, if they say yes, questioning stops, if they say no,
they are offered a lower Amount B. They say either yes or no to Amount
B and then questioning stops. So there are three possible outcomes:
Yes; No-Yes; No-No.

I would like to run an ordered logit or ordered probit model where
these outcomes make up the independent variable. To complicate things,
there are 4 possible starting values of Amount A.. Each respondent is
randomly assigned one of the values.

My question is how can I take into account that there are different
values of Amount A (and subsequently B)? Is it to do with groups? Or
do I need to write a program?

As you can no doubt guess, my experience with this is quite limited,
so any information at all would be greatly appreciated.

Thanks!
Coba
*
*   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/




The University of Aberdeen is a charity registered in Scotland, No SC013683.

<<winmail.dat>>




© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index