Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: spike model for DB CV survey


From   Austin Nichols <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: spike model for DB CV survey
Date   Sun, 25 Sep 2011 08:06:08 -0400

Kifle Wondemu <kiflea@gmail.com> :
http://fmwww.bc.edu/repec/bocode/d/doubleb.html
indicates that this is an interval regression model assuming normality.
It seems official -intreg- could be used to estimate this model.
If the unobserved true outcome (WTP) cannot be negative, then the assumption
of normality is untenable, and you should specify an alternative distribution
when you write out a -ml- model. Or

findit censored poisson

On Sun, Sep 25, 2011 at 12:01 AM, Kifle Wondemu <kiflea@gmail.com> wrote:
> Hi folks,
>
> I want to use a spike model to deal with zero response for double
> bounded dichotomous choice contingent valuation survey. The existing
> DOUBLEB user written program, if I am correct, does not differentiate
> genuine zeros from the protest ones. When I use doubleb on the whole
> sample, I am getting a negative willing to pay which is not
> theoretically tenable in my case.
> I would appreciate if anyone is aware of any user written program that
> can resolve my problem.
> Thanks
> Kifle Asfaw
*
*   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/


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