That's exactly right.
Kosuke
> > By the way, for this question, you
> > should NOT use the R built-in function.
>
> are you refering to rt?
>
>
>
> Quoting Kosuke Imai <kimai(a)fas.harvard.edu>:
>
> > You should simulate the variance separately for each draw: otherwise, it
> > will be a normal distribution where the variance is fixed. We want to let
> > the variance to vary for every draw so that t-distribution has more
>
> >
> > Kosuke
> >
> > On Sat, 15 Feb 2003, Mee-Jung Jang wrote:
> >
> > > For part 3a. Central Limit theorm, do we do a separate draw for the
> > > variance for each draw from the student t distribution? or do we do one
> > > draw and use that to do all 1000 i.d.d?
> > > thanks,
> > > mee-jung
> > >
> > > _______________________________________________
> > > gov2001-l mailing list
> > > gov2001-l(a)fas.harvard.edu
> > > http://www.fas.harvard.edu/mailman/listinfo/gov2001-l
> > >
> >
> > _______________________________________________
> > gov2001-l mailing list
> > gov2001-l(a)fas.harvard.edu
> > http://www.fas.harvard.edu/mailman/listinfo/gov2001-l
> >
>
>
if you're looking for me to approve your paper, please feel free to just
stop by my office 34 Kirkland st (which is easier for me than making an
appointment). normally it only takes a few minutes and is usually the
best strategy. alternatively, you can email me a pdf of the article and
we can do it virtually.
also, I'm out of town Wed-Friday of next week.
see you Monday..
Gary
: Gary King, King(a)Harvard.Edu http://GKing.Harvard.Edu :
: Center for Basic Research Direct (617) 495-2027 :
: in the Social Sciences Assistant (617) 495-9271 :
: 34 Kirkland Street, Rm. 2 HU-MIT DC (617) 495-4734 :
: Harvard U, Cambridge, MA 02138 eFax (928) 832-7022 :
When I open a file to compose R functions (usually I call it junk.R), I am
no longer able to C-c C-l to load it into R. Nor does it automatically
indent my functions when I type them. Any suggestions?
It was working fine for hw 1.
Andrew
--
Andrew Reeves
reeves(a)fas.harvard.edu
617.493.3485 tel.
301.639.8369 cell.
http://people.fas.harvard.edu/~reeves/
I'm still having trouble using ess. When I type my code into the scratch
buffer after saving it as an "Rdata," it doesn't tab at all. If it's a .tex
file, the tabs work like normal tabs, not "smart" tabs. How do I get ess to
work?
Thanks,
Phillip.
-------------------------------------------------
Phillip Y. Lipscy
Perkins Hall Room #129
35 Oxford Street
Cambridge, MA 02138
(617)493-4893 DORM
(617)851-8220 CELL
lipscy(a)fas.harvard.edu
http://www.people.fas.harvard.edu/~lipscy/
First Year Student, Ph.D. Program
Harvard University, FAS, Department of Government
-------------------------------------------------
There is an error in my solution set handed out in the section last week.
In 1(a), "if(max(member)<dem" should be replaced with
"if(max(member)<=dem" The corrected version is now on the course website.
Thanks to Jeniffer and Carrie for pointing this out!
Good luck with your second homework!
Kosuke
this would be good for you all if you have the time. its good to imagine
what it will be like when you'll be in this situation -- just like high
jumpers are taught to imagine making it over the bar repeatedly in their
mind...
Gary
---------- Forwarded message ----------
Date: Wed, 19 Feb 2003 17:01:12 -0500
From: Ruth Kolodney <kolodney(a)latte.harvard.edu>
To: Gov_Grads(a)latte.harvard.edu, Cbrss_affiliates(a)latte.harvard.edu
Cc: Gary King <GKing(a)latte.harvard.edu>
Subject: Job candidate for quantitative political methodology position
Dear Government Graduate Students,
Kevin M. Quinn, a short-listed quantitative political methodology candidate
for a junior faculty position in the Government Department, will be
visiting Harvard on Friday, March 14. Please attend his job presentation if
you can:
Kevin M. Quinn (Ph.D. Washington University, St. Louis; currently Assistant
Professor, Department of Political Science, University of Washington)
Date of Full Day Visit, Friday, March 14
Title of Job Talk: "Re-Examining the Impact of Public Opinion on U.S.
Supreme Court Decision-Making"
Location: CBRSS, 34 Kirkland Street
Time: 10:30-12
Please contact me at 496-1512 or kolodney(a)hdc.harvard.edu if you would like
to sign up to attend his candidate-student breakfast or if you have any
other questions. The breakfast is scheduled on the day of
his visit--Friday, March 14--from 8:30-9:45 at the Inn at Harvard.
Sincerely,
Ruth
Hi, I am a 4th year grad student in the political science dept at Brown and am in the beginning stages of writing my dissertation. I am writing it on the intersection of institutions, political participation, and race. I have been looking at some of the Verba, Schlozman, Brady articles, as well as others. If you'd be interested in working on an aritcle in these areas, let me know. Also, I am new to R, so working w/ someone who is familiar w/ it would be helpful. Thanks, Carrie
Hi, all. I am looking for a partner for the final paper. I am a fourth-year grad student at Brown, and I would like to work on an article that is relevant to my dissertation. My topic is comparative political socialization/social capital in industrialized democracies (particularly related to young people). I am working largely with national panel surveys. I have picked out a few articles that might be good to analyze, including one by Ronald Inglehart and two by David Sears, but I am open to other possibilities. If any of this sounds interesting to you, please let me know. But I should note that I am new to R.
Thanks. Hope everyone made it through the blizzard intact!
-Jennifer
Hi everyone,
If you haven't found a partner for your term paper project yet, let me
know as soon as possible. Also, if you have found a partner AND a paper to
work on, stop by Gary's office to get his approval by next Wednesday!
Finally, please make sure you include the citation of the paper and the
name of your partner in your answers to Assignment 2.
Thanks!
Kosuke
(possibly) easy plotting question:
I would like to produce a "split" plot, with the top part a scatter plot
with fitted model, and the bottom part a scatter plot of the residuals--both
plots with the same X-axis. I know I can do a split.screen, but I do not
want two plots separated by space and the like. If it is easy to adjust the
screen sizes in split.screen so to produce this effect, that would be fine
too. It's not clear what the easiest way to do this is though. Any
suggestions?
Thanks,
John.