This is a good question, Zac, probably something we should all talk
about in person at greater length (perhaps saturday). And there are a
lot of angles and ways of answering the questions. What works for me is
to look broadly across disciplines. I've given talks to CS depts
regularly and communicate with these folks, but they have a different,
altho related, mission.
overall, there are spectacular advances in many fields, but most of
those making such advances are narrowly focused on what they're doing.
(they have to be; otherwise, they wouldn't have been able to accomplish
the task!) as such, they're not necessarily focused on the big picture,
how what they're doing in CS could help you in polisci, or how it would
solve problems they don't know about. So that means you can make some
advances by connecting things and ideas and fields that haven't been
connected. The key is to figure out how to do the translation to span
the different areas.
Here's one example related to your question of how I took neural network
models and translated them into a plain old statistical model with a
likelihood. This is also a good example for class, since any of you
could now read this paper and would have no trouble very quickly
understanding what NN models are (in addition to sounding exceptionally
cool), although reading the original NN papers in computer science would
be more of a pain because they use such different language and
notation. see: Nathaniel Beck, Gary King, and Langche Zeng. "Improving
Quantitative Studies of International Conflict: A Conjecture," American
Political Science Review, Vol. 94, No. 1, (March 2000): 21-36,
http://gking.harvard.edu/files/abs/improv-abs.shtml.
overall, its impossible to stay on top of all these literatures, or even
just the political science literature. its way too vast and progresses
way too fast. You have to pick and choose. and if you do have a
hammer, there's absolutely nothing wrong with looking for some nails
that need hitting! sometimes you have a problem with no method; other
times you have a method and no problem; sometimes you have an idea, and
a method but no data, etc. you have to fill in the pieces in whatever
order you can find them. There's no reason to think that one order is
better or more scientific than others.
Gary
---
http://gking.harvard.edu
On 04/24/2009 04:03 AM, Z. A. Townsend wrote:
I have a question that I wanted to ask Gary that has
to do with
developing research questions in methodology itself, but I figured I
might as well do it here on the list in case others are interested.
I have a background in some "machine learning" (SVMs, the Ising model
and exact sampling, MCMC, k-nearest neighbor, HMMs), but have seen and
used those methods in relation to classic problems, e.g. vision, image
processing, robotics, and natural language processing.
I was wondering if you could provide insight into how to bring
complicated, difficult to understand methods from more "technical"
fields like computer science and statistics to political methodology?
I see two possible routes: (1) Do you stay on top of the statistics
and comp sci literature as it's developing and then say "oh this might
apply to this problem in political science"? Or (2) is it more often
the case that you see some problem in the political science lit or the
real world, and then you search for solutions to those in other
fields? How fruitful is it to look to what others have done outside
political science vs. spending the time to try to come up with your
own algorithm or model?
You seem to develop many methods on your own, do computer scientists
every come look at your work and say, "wow, this solves a problem
we've been having"? I know we're all in universities because being
around other scholars makes everyone more productive, but how much do
the social scientists and the computer scientists interact, for
example?
To give a concrete example, I've been thinking about this as I go over
hidden Markov models in my artificial intelligence class (here at
Brown). So if you assume that some process is a Markov process with
unobserved states, one of the conical problems is to figure out from
some output sequence the most likely state transitions and output
probabilities. To solve this most people use a special case of the EM
algorithm, which is what brought these two separate classes together
for me. So I have this model that has been shown to be useful in gene
prediction, cryptanalysis, and such things, and it seems like there
could be some real political science applications but I'm not sure
what those are exactly. This is a case where I'm operating under the
first method from above-- I've found some cool solution to a problem
I'm not sure I have, although I often think the second method from
above makes more sense.
To give a slightly more personal explanation for my curiosity:
substantively I'm interested in what are often thought of as political
science questions, but I get this relative joy in reading statistics
and computer science articles, and I'm trying to figure out how to
bring that together. You've given us a lot of intuition and skills to
take substantive empirical questions and develop methods to solve the
wide variety of problems we might have, but how do wake up one day
with the goal of creating a new clustering methodology or trying to
model something using an HMM when few people in political science even
know what those are?
Cheers,
Zac
_______________________________________________
gov2001-l mailing list
gov2001-l at
mailman.fas.harvard.edu
http://mailman.fas.harvard.edu/mailman/listinfo/gov2001-l