Hi folks,
I have a SAS dataset (.sas7bdat) that I want to import into R but I don't
have SAS on my computer, and I can't find any SAS data viewers for a Mac in
order to export the data to a CSV file. Has anyone dealt with this problem
before? Any advice?
Thanks,
Colin
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Hi everyone,
For our replication paper we're trying to do matching with CEM and running
into some coding issues:
We want to do two things with CEM, one of which we can do with the cem()
command and one with the matchit() command, but we're trying to figure out
how to do both with only one or the other. We want both: (a) to be able to
use our matched data in zelig so we can do all the cool things with zelig,
like setx(), etc, after we run our final model with the matched data. We can
get information to pull into zelig from matchit() but not from cem(). (b)
When we use cem() it, by default, matches each treated case to ALL controls
in each treated case's stratum. In matchit() it by default only does a 1:1
match with the nearest control case within the stratum. (we have many more
C's than T's in the area of common support. going to 1:1 means throwing out
hundreds of observations)
Is there a way to pull cem() output into a zelig model? OR Is there a way to
change matchit()'s default settings to get the 1:(whole stratum) matching
when method = "cem"?
Thanks,
- Noah and Julie
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Hey Class -
In the interest of exploiting our resources to the fullest, I'm up for a
section on spatial statistics. I'll collect interested parties (off the
general list!) to gauge interest, and then work on scheduling from there.
If there's a good chance you'll come to a conveniently scheduled section,
just shoot me an email.
Thanks,
Colin
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Gov 2001,
I'll be covering basic Bayesian Data Analysis in section on the 27th
(completely optional). It will be video taped for extension school
students. As I mentioned in section the vote was extremely close with
almost everyone voting. Never one to get in the way of learning, I'm happy
to give an additional section on text analysis or spatial statistics. If
anyone wants to organize it, just give me a time and evidence that at least
10 people will show up and I'll reserve a room etc. Regardless, you are
also always welcome to come by office hours to talk about (my opinion of)
the best resources to learn more about these topics.
For the Bayesian lecture, if there is anything in particular that you want
to see, send me an email off list. If it is feasible and applicable to the
majority of students, I'll try to work it in!
I can't tell you guys how excited I am about your interest in additional
sections. It makes me really happy how interested many of you are in the
material.
Good luck on your papers! I can't wait to read them.
Brandon
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Not really a statistics announcement but for those who, like me, use
TexMaker for LaTeX, v 3.0 has just been released. It includes a very nice
PDF viewer inside the editor which is awesome. Just thought people might
want to know:
http://www.xm1math.net/texmaker/
Brandon
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Hi Class,
I was having issues getting CEM to run on my MAC over the weekened,
which ended up prompting a email chain with our TFs, Gary, and one of
Gary's co-authors. We finally figured out the issue, and Molly
suggested that I sent out the solution to the class because she also
had the same thing happen when trying to use CEM on her MAC.
Essentially the issue is that after running "library(cem)", using any
commands that required CEM would result in R freezing and the mac
colorwheel would just keep going when trying to use R.
The solution to this problem is to download the latest version of R,
2.12.2 from http://software.rc.fas.harvard.edu/mirrors/R/ (I had only
downloaded R on this computer at the start of this semester, and this
version is new since then). Then after that has downloaded, to go to
the development tools section of the cran website
(http://software.rc.fas.harvard.edu/mirrors/R/) and download
tcltk-8.5.5-x11.dmg. After both of those things are downloaded, when
you run R, before you load CEM, you have to run "library(tcltk)".
After that, if you then run "library(cem)" everything will work fine.
Anyway, hope this helps for anyone else that has a MAC and is having issues.
Adam
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
--
gov2001 mailing list served by Harvard-MIT Data Center
List Address: gov2001(a)lists.gking.harvard.edu
Subscribe/Unsubscribe: http://lists.gking.harvard.edu/?info=gov2001
Hi everyone --
Just a reminder that there is a Gov 2001 party at Gary's house on April 23rd
at noon. You can find directions to Gary's house at
http://gking-projects.iq.harvard.edu/directions/. Remember to respond to
the RSVP on the course website so we can get a head count. We'd love to see
you all there!
Molly
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Gov2001,
Molly and I have been looking through your re-replication memos and I have
to say that we are just blown away by the effort you all put in to them. We
know that the workload in the class is taxing you heavily, but you still
found time to put together insightful, thorough, and kind comments on the
work your colleagues are doing. I saw memos that were better than any
referee report I've ever gotten.
We hope that getting some outside feedback has re-energized you all as you
move forward on your papers. We are really excited to see the final
products.
Bravo!
Brandon and Molly
P.S. Don't forget to respond to the two polls on the homepage: one about the
final section and one an RSVP to our end of the year party. Molly will be
sending out an email with more details on the party including directions to
Gary's house etc.
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Gov2001,
I got the following question from Julie over the weekend (which I reprint
here with her permission):
"I am wondering if you guys have any advice for another stats course I
should take next. While I feel fairly comfortable with the material covered
in GOV2000 and GOV2001, I kind of just want to go over it all again and get
more practice applying this stuff. Any suggestions?"
I figured others might be interested in the answers as well (hence the email
to the list).
First, let me say that I think this question is posed in exactly the right
way. Even though you are "comfortable" with the material in 2000 and 2001
its useful to learn it again in another setting. When I've spoken with Gary
about his methods education in grad school, that's what he told me he did.
He just went to a bunch of different departments and took classes teaching
basically the same material from different traditions. So just because
you've already covered Generalized Linear Models in this class doesn't mean
you should shy away from taking a GLMs course in the stats department.
Let me start by giving the short, direct answer: Stat 149/249 is the
statistics department equivalent of this class. It covers generalized
linear models from quite a different perspective (closely following the
canonical textbook McCullagh and Nelder if that helps). If you want to
review material in this class and get more practice. This is the way to do
it.
Now for the longer answer. Generally speaking the major choice you have to
make is which department to take the class in. The economics perspective is
very different from the statistics perspective (for example). In fact you
see the hallmarks of both traditions in political science. My background
has favored that statistical over the econometric approach, so my apologies
if my answer is a bit biased (note my answer is also poli-sci biased and
Harvard-centric because that is what I know!). Here are some thoughts on
individual classes though:
1. Stat 110: Taught by Joe Blitzstein this is the introduction to
probability. There is no data in this course so you won't get "practice in
application" but it gives you a much firmer understanding of probability and
the distributions that we assume for the data in generalized linear models.
I think everyone interested in methods should take this class.
2. Gov 2002: Taught by Adam Glynn and Arthur Spirling. This class is an
overview of various methods focusing mostly on causal inference and light
Bayesian analysis. Definitely worth taking if you want to learn more about
causal inference. As it currently stands its more of a reading seminar than
a practical applications course.
3. Stat 139/239: This class covers linear regression from the statistical
perspective. Useful if you want to practice what you learned in Gov2000 but
I think you could skip it and go straight to...
4. Stat 149/249: This class covers generalized linear models. Its the
closest approximation to Gov2001 in the stats department. You cover a lot
of things traditional to GLMs not covered in this class including the
exponential dispersion family, Fischer scoring and analysis of deviance. It
also helps you to pick up on nuances in the material you might have missed
the first time around!
5. Stat 220: Bayesian Data Analysis. When you are ready for serious
Bayesian work this is the course for you. It helps to already know some
Bayesian statistics going in.
6. Stat 221: Statistical Computing with Edo Airoldi. If you are going to do
methods seriously: take this class. It helps cement the practical
logistical issues of Bayesian model estimation, EM, coordinate ascent etc.
7. Econ 2140: Econometric Methods with Guido Imbens. This is similar to a
Gov2001 type class but taught from the econometric perspective. Imbens is
great but it helps to have a firm foundation befroe going in.
8. Econ 2142: Time Series with Jim Stock. If you are interested in doing
Time Series consider taking this course. Jim Stock is probably the top time
series researcher in the country so its an awesome opportunity. The Stats
department also offers a time series class but it tends to be geared towards
situations with considerably more data than we typically have (e.g. if a
machine produces a thousand widgets per minute...etc)
9. Sociology 275: Social Network Analysis with Peter Marsden. This is a
great class for learning about network analysis.
More than anything else the key is to just start reading into different
literatures. Come to Gov3009 (Research Workshop in Applied Statistics) and
read Political Analysis or other methods journals. At a certain point you
obviously have to stop taking classes- but once you have Gov2001 and a firm
background in probability theory- you should be able to read into any
literature with enough time.
If you have thoughts on other classes or questions about a specific class,
send it out to the list. Also feel free to come talk to me during office
hours (I've taken quite a few stats classes here).
Brandon
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Gov 2001,
Wow! Almost the entire class responded to the survey expressing interest in
coming to one of the optional sections! That's so cool! You guys are the
best. I wish we had time to do one lecture on all the major vote getters,
but we really don't (and I imagine interest would wane after the third or
fourth "final section").
So there were three topics which each got more than 15% of the vote. I've
put up a new poll (same place) that asks you to pick your favorite of these
three categories. We are doing this for two reasons: (1) We want the topic
people are most interested in, not just the one the most people will attend,
(2) some people mentioned that they didn't know what all the topics meant.
So here is a brief summary of the top 3:
Bayesian Statistics: We will cover the Bayesian approach to data analysis
focusing on the differences with the frequentist statistics covered in
class. We will outline MCMC methods and provide some applications for which
Bayesian methods might be useful. Finally we will direct you to resources
for more information and take questions.
Spatial Statistics: We will cover spatial data and basic visualization in R,
the spatial autoregressive model and how to choose spatial weights (with a
focus on the international relations context but its generally applicable).
We will then direct you to the canonical resources for more information and
take questions.
Applied Text Analysis in R: We will cover two kinds of text analysis on the
last day of lecture. In this section, we will show you how to apply some of
these methods in practice. We will provide a quick summary of the
literature and then mostly show code for exploring textual data, visualizing
textual data, supervised learning (document classification) and unsupervised
learning (clustering).
If you have any questions feel free to shoot me an email. Go vote on your
favorite. I'll announce the winner next week.
Also thanks to everyone who suggested additional topics: anchoring
vignettes, GIS, IV, regression discontinuity, structural equation modelling,
selection models and time series were all suggested. If you want to talk
about any of these things- come see me in office hours. I can direct you to
useful resources.
Brandon
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
