Re: st: impute with draws from random distribution

[D-Ta <altruist81@gmx.de>]

I see your argument. However, if you argue that programm participation 
has a random component, it should be valid to predict a hypothetical 
(counterfactual) starting date for non-participants (who could 
-potentially- well have participated). This kind of approach has been 
taken by other papers, such as (Wunsch & Lechner, 2008, Kyklos) or 
(Lechner & Wunsch, 2009, Journal of Labour Economics).

Otherwise, the start date cannot be used as a control variable in the 
matching approach. With your advice to generate dummies for missing 
values (and to control for those) you cant (by definition) reach common 
supported between the treated and the comparison group.



Am 22.06.2011 11:07, schrieb Maarten Buis:
> On Wed, Jun 22, 2011 at 10:03 AM, D-Ta  wrote:
> > The sample consists of of individuals (with covariates x1 and x2) who can
> > either be participating in programm 1, programm 2, or be non-participants.
> > The non-participants are my controll group. One of the control variables
> > that I would like to condition on in a subsequent matching step is time to
> > participation. By definition, time to participation is not observed for the
> > non-participants. Hence, I would like to create hypothetical values in that
> > variable for the group of non-participant. It is standard in the literature
> > to randomly draw from the distribution of the participants.
>
> It is absolutely wrong to try to impute values that for logical
> reasons cannot exist. This is a case where the "dummy variable method"
> for dealing with missing values is valid. See for example footnote 4
> in Paul D. Allison (2002) Missing Data, Quantitative Applications in
> the Social Sciences 136. Thousand Oaks: Sage.
>
> 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/
*
*   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/