Sheena and didi, responses below:
First,
are we doing it for the entire dataset or just for the zelig model?
And
As it says, you want the counterfactuals for all observation (so no model
needed at all).
second, the way I understand it, we're trying
just to get a percentage
- so
what goes in the table?
just report the percentage of obs for which the counterfactuals wall within
the convex hull. You don't need to put this in a table if you don't want.
jens
-----Original Message-----
From: gov2001-l-bounces at
lists.fas.harvard.edu [mailto:gov2001-l-
bounces at
lists.fas.harvard.edu] On Behalf Of Sheena E Chestnut
Sent: Friday, April 18, 2008 12:25 PM
To: gov2001-l at
lists.fas.harvard.edu
Subject: [gov2001-l] Counterfactual questions
Hey all -
To follow up on Didi's questions from yesterday, I'm also having
trouble
understanding what we're meant to be doing on the counterfactual in 1c.
Any help resolving my confusion would be much appreciated!
Thanks,
Sheena
Dear List (again),
So, in 1C, are we supposed to do counterfactuals for the entire
dataset or
just
for the data we used in the zelig model?
gracias
d
_______________________________________________
gov2001-l mailing list
gov2001-l at
lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
_______________________________________________
gov2001-l mailing list
gov2001-l at
lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l