Hi everyone,
You may already know about this, but I wanted to share a R package that I've
found very useful - apsrtable. It works like xtable, but the output looks
more professional and you can export multiple models to a table at the same
time. The only catch is that in Latex, you have to type
\usepackage{dcolumn} at the top in order to recognize the tables.
Also, if you need to rotate a table sideways in Latex, you type
\usepackage{rotating} at the top of the document and then
\begin{sidewaystable} instead of \begin{table} when you want to start a
sideways table.
Best,
Erin
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Hi everyone --
No matter whether you are going mountain biking or not, we'd like to invite
you all to lunch afterwards. We'll be meeting at Stone Hearth Pizza,
located at 974 Great Plain Avenue, Needham, MA, at noon on Sunday. We'd
love to see you there! Let me know if you are planning on coming so we can
plan numbers.
Also, if you still want to go mountain biking, it's not too late! Let me
know if you do.
Molly
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Hi Everyone!
I hope your re-replications are going well. I wanted to:
1. Review the schedule for the rest of the semester.
2. Solicit requests for the final section.
3. Let you know I'll be off email for the next few days
1.
For the schedule, here are the key dates that remain:
April 4- Rereplication due
April 13- Pset 7 (Part 1) due
April 20- Pset 7 (Part 2) the code project due
April 28 5 P.M.- Final Paper Due
May 9 - Your comments on another student's paper due
2.
We have three more regular sections and then in theory there would be
section April 27. However, I know that's crazy due to the replication
papers being due on the 28th. However, we wanted to offer some potential
topics. There is a quiz on the main page of the website. Fill it out if
you would be interested in coming and let us know what you'd like to hear
about. If there is enough interest in a particular subject, we will hold
section. Please respond soon as we have to let the videographer know
whether or not we need him here that day. The choices are:
-Bayesian Statistics (in an hour)
-Ecological Inference
-Open Q&A
-Applied Text Analysis in R
-Topic Models for Text
-Spatial Statistics
-Additional Likelihood Models (Gamma, Cox-Prop. Hazards etc.)
Also we created a text box if you want to suggest other options. If they
seem like they would have broad appeal I will add them to the list. While
all these topics have technical details, we will aim to pitch the lecture at
about the same technical level as section has been at. If a bunch of you
want to rally together to request a really technical topic like EM,
statistical computing etc. that's fine too just let me know. For reference,
the regular remaining sections will cover:
-Causal Inference (An Overview)
-Multiple Equation Models
-Missing Data
3.
I am visiting my fiancée this weekend so I won't be responding to emails
with my usual speed (if at all). So if you are in a time crunch I recommend
you CC Molly or send it to the list. If it can wait you are still welcome
to email me and I'll respond to everything when I get back.
Have a good week everyone!
Brandon
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Hi Class,
I keep receiving this message when I try to optimize my function in problem
2.4:
Error in optim(par = rep(0, 8), y = y, X = X, Z = Z, fn = zero.poiss, :
non-finite finite-difference value [6]
I've checked my function to make sure all the parts of it are working
correctly, I've tried changing things in optim. I think we talked about
this error is section once- can anyone tell me what's going on?
-Adela
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Hi Brandon,
Do we have to make education and income as.factor levels for the first
question? It works to run zelig like this, but i am getting this strange
error when i try to do the first differences:
> x.high <- setx(z.out, data=final.data, educ=7)
Error in `contrasts<-`(`*tmp*`, value = "contr.treatment") :
contrasts can be applied only to factors with 2 or more levels
Thanks!
Slawa
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Hi all,
In 2.5, why it is unnecessary to simulate from the zero-inflated poisson
distribution?
Thanks, Yanfang
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Hi Everyone!
Quick correction to Problem 1.2 on the homework. In the problem we ask you
to "Simulate first differences in levels of attention to the campaign when
going from the lowest to the highest educational category, holding all other
covariates at their means." Holding income at its mean is nonsensical
though since its an ordered factor. Zelig will actually hold ordered
factors at its median by default (which is what you should do).
Most of you probably didn't notice, but it was brought to our attention by a
student who was valiantly trying to get Zelig to do what we'd actually said
to do. Sorry about that!
Brandon
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
I'm lecturing in class today; if you'd like a print out of the slides in
front of you (not necessary but fyi), they are the second under causal
inference at http://j.mp/h9qFu3, but be sure to hit refresh first.
Gary
--
*Gary King* - Albert J. Weatherhead III University Professor - Director,
IQSS - Harvard University
GKing.Harvard.edu <http://gking.harvard.edu/> - King(a)Harvard.edu -
@kinggary<http://twitter.com/kinggary>- 617-500-7570 - Asst 495-9271 -
Fax 812-8581
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Hi everyone, I'm going to ask you near the start of class for any good
stories you have about trying to get data and replicate the results for your
papers. please bring in the stories. Its very useful for us all to hear.
See you soon...
Gary
--
*Gary King* - Albert J. Weatherhead III University Professor - Director,
IQSS - Harvard University
GKing.Harvard.edu <http://gking.harvard.edu/> - King(a)Harvard.edu -
@kinggary<http://twitter.com/kinggary>- 617-500-7570 - Asst 495-9271 -
Fax 812-8581
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l
Hi Gang, might anyone have an idea how to solve a little latex problem? The
attached file an example. Its for a presentation (and uses 'beamer') and so
you might not have had experience with that, and of course I have had lots
but I can't figure it out.
Attached is a tex file. If you latex it, the page number on the bottom
right says "/3" on every page. If instead you comment out the title,
author, and date, and re-latex it, you'll wind up with the behavior I want,
which is [current page number]/[max page number], and when things happen on
one page, it doesn't increment the page number.
But I need a title page! Any ideas?
Thanks,
Gary
--
*Gary King* - Albert J. Weatherhead III University Professor - Director,
IQSS - Harvard University
GKing.Harvard.edu <http://gking.harvard.edu/> - King(a)Harvard.edu -
@kinggary<http://twitter.com/kinggary>- 617-500-7570 - Asst 495-9271 -
Fax 812-8581
_______________________________________________
gov2001-l mailing list
gov2001-l(a)lists.fas.harvard.edu
http://lists.fas.harvard.edu/mailman/listinfo/gov2001-l