This is a bit strange. I can't replicate it using the demo. Try
installing the latest version of Zelig (which we just uploaded a few days
ago), and see if the problem still persists. Make sure that you have a
factor variable as the dependent variable: use as.factor().
Kosuke
--
Department of Politics
Princeton University
http://imai.princeton.edu
On Thu, 15 Oct 2009, Donald Braman wrote:
Even though there are only six possible values in my
ologit esitmates, I get
seven values in the qi$ev:
s.out$qi$ev
1 1 2
3 4 5 6
1 0.0037076 0.23622 0.14601 0.16821 0.18050 0.14410 0.12126
2 0.0033500 0.23162 0.11705 0.15862 0.20940 0.14789 0.13207
3 0.0020180 0.12770 0.08862 0.12422 0.18882 0.19016 0.27845
4 0.0022673 0.21746 0.12485 0.15439 0.19608 0.15260 0.15235
5 0.0031793 0.28474 0.14091 0.15632 0.18133 0.13101 0.10251
6 0.0024818 0.19614 0.11684 0.15278 0.22823 0.16162 0.14190
7 0.0039682 0.26576 0.13108 0.15688 0.19080 0.12478 0.12674
8 0.0015015 0.15490 0.09352 0.13356 0.23033 0.19183 0.19436
9 0.0027922 0.18692 0.11385 0.17334 0.20004 0.14274 0.18032
10 0.0032175 0.19282 0.12555 0.14715 0.20266 0.17849 0.15011
That's odd, isn't it? Why two columns of 1's? The same thing happens
for
qi$fd.
I can send more code if need be, just curious if anyone has run into this
before.
Donald Braman
phone: 413-628-1221
http://www.culturalcognition.net/braman/
http://ssrn.com/author=286206
http://www.law.gwu.edu/Faculty/profile.aspx?id=10123
-
Zelig Mailing List, served by Harvard-MIT Data Center
Send messages: zelig(a)lists.gking.harvard.edu
[un]subscribe Options:
http://lists.gking.harvard.edu/?info=zelig
Zelig program information:
http://gking.harvard.edu/zelig/