Hi Han-
The signs of your coefficients are consistent with mine. I believe lower
numbers on the attention scale indicate higher levels of attention, so
negative coefficients for those variables are reasonable.
Best,
Megan
On Wed, Apr 7, 2010 at 8:58 PM, Han He <han.he at college.harvard.edu> wrote:
Hi,
Is anyone else getting weird numbers for 1c? For some reason,
education, contact, income all seem to have negative coefficients.
Is this consistent with what you guys are getting?
Han
Harvard College Class of 2013
614-329-1324
On Wed, Apr 7, 2010 at 9:09 AM, Zuzul, Tiona <tzuzul at hbs.edu> wrote:
Meryl,
You?re getting this response because turnout is not an ordered factor
variable. I believe the dependent variable in 1C is attention. Hope this
helps!
Tiona
From: gov2001-l-bounces at
lists.fas.harvard.edu
[mailto:gov2001-l-bounces at
lists.fas.harvard.edu] On Behalf Of Meryl
Federman
Sent: Wednesday, April 07, 2010 12:48 AM
To: Class List for Gov 2001/E-2001
Subject: Re: [gov2001] oprobit?
Hm... now I'm getting "response must have three or more levels" when I
attempt finaldata2 <- zelig(as.factor(turnout) ~ attention + contact +
educ
+ income + black + age + dem + rep + lib + con +
black:contact, data =
final.data, model = "oprobit")
If this looks familiar to you, let me know, if no, that's fine, just
thought
I'd run it by you. Thanks again for all your
help!
~Meryl
On Apr 6, 2010, at 8:59 PM, Akihiro Nishi wrote:
Hi
Instead of the outcome name, y, as.factor(y) will work. Please try!
Akihiro
>> Meryl Federman <federman at
fas.harvard.edu> 04/06/10 8:52 PM >>>
For 1C - using the zelig with
just saying "oprobit" instead of
regular probit throws "response must be a factor".
I've poked around a bit but haven't found the right thing yet...
Any thoughts?
~Meryl
_______________________________________________
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
_______________________________________________
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