Hi,
I had another look over GenMatch. It looks to me as though it is nothing more
than a stochastic beam search for Euclidean distance metrics. Surely I must be
missing something.
Geoff
Hi list,
a quick question,
In some funtion I am trying to implement, R is telling me that "m must
be positive", and m is defined:
k<-exp(par[2])
betas<-par[3:7]
lambda<-exp(-(x%*%betas))
m<-k/lambda
can anyone think why I am getting negative m's?
Thanks,
Juan
Hi,
I downloaded the library 'rmutil' and wnat to have a look at its
documentation, which is on the website of the author under the extension
.tgz.
Does anyone know how to open and view such files?
Thanks,
Juan
If any of this doesn't make sense, please let me know.
The _convex hull_ is the set of points at the border of the _convex set_ (which
is a set of space and does not appear to be defined in the current version of
the Oxford English dictionary). The convex hull occupies no space, but
contains all of the points.
Hi All,
Just a quick reminder that my office hours will be Friday from 4 - 6 PM in
the main concourse-level computer lab in CGIS North (and not today). My
regular Wednesday office hours will resume next week.
Best,
Dan
----
Ph.D. Student
Department of Government
Harvard University
Tutor, Currier House
dhopkins(a)fas.harvard.edu
http://www.danhopkins.org
Hi Holger,
I'm "cc"ing the list since that's an entirely reasonable pair of
questions. Yes, we mean comparing the world where we see these same
observations with all treatment indicators set to 0 to the world where all
treatment indicators are set to 1. And by original sample, we mean three
separate samples: the mail sample (assigned to treatment of one mailing
and controls), the door sample (assigned to treatment of one door-knock
and controls), and the phone sample (assigned to one phone call vs.
controls).
Best,
Dan
----
Ph.D. Student
Department of Government
Harvard University
Tutor, Currier House
dhopkins(a)fas.harvard.edu
http://www.danhopkins.org
On Mon, 17 Apr 2006, Holger Lutz Kern wrote:
> Hi Dan and Ian,
>
> I have a question about ps 7 (a). I
> estimated the ITT for each of the three
> treatments, but am having trouble
> understanding what you want us to do
> next. Specifically, what do you mean by
> the first difference in this case?
> Comparing a world in which no one was
> assigned to the treatment to a world in
> which everyone was? And does whole
> sample refer to the original sample with
> multiple treatments or the "door",
> "mail", "phone" subsamples that we
> constructed?
>
> best,
> Holger
>
>
> --
> Holger Lutz Kern
> Graduate Student
> Department of Government
> Cornell University
>
> Institute for Quantitative Social Science
> Harvard University
> 1737 Cambridge Street N350
> Cambridge, MA 02138
>
> www.people.cornell.edu/pages/hlk23
>
>
Hi,
Considering that no one specified 4 for COST (and trying to pull out an absolute
scale is ridiculous in this situation), we should not calculate first
differences between COST=3 and COST=4, correct?
Geoff
Hi all,
The question says that "y_i = 1 when y_i^* > 0 and 0 otherwise." Could you
tell me if it is correct?
I feel that it might be "y_i = 0 when y_i^* > 0 and 1 otherwise" rather than
"y_i = 1 when y_i^* > 0 and 0 otherwise" in order to approximates the probit
model because the observation mechanism for the probit model is is y_i = 0
if y_i^* > \tau and 1 otherwise where y_i is observed realization , y_i^* is
unobserved variable, and \tau is the threshold parameter.
Thanks,
Yuki
Hi all,
for ps 6 (f), I'm trying to estimate the
optimal number of degrees of freedom.
The problem is that my estimates are
quite dependent on the starting value
that I give optim. I've tried several
methods but they all produce unstable
results even after setting maxit=10000
so that convergence takes place. Does
anyone have any suggestions what to do?
Thanks,
Holger
--
Holger Lutz Kern
Graduate Student
Department of Government
Cornell University
Institute for Quantitative Social Science
Harvard University
1737 Cambridge Street N350
Cambridge, MA 02138
www.people.cornell.edu/pages/hlk23
Hi Jacqueline,
Yes, it is fine if you use Zelig for part (f).
Best,
Dan
----
Ph.D. Student
Department of Government
Harvard University
Tutor, Currier House
dhopkins(a)fas.harvard.edu
http://www.danhopkins.org
On Fri, 14 Apr 2006, Jacqueline Chattopadhyay wrote:
> Hi Dan and Ian,
> I know that we can't rely on Zelig for PS 6, except to check answers, but
> does this mean that Zelig-generated graphs are also banned for part
> (f)--comparing models and explaining which one to choose?
> Thanks,
> Jacqueline
>