statistics with applied social science focus

[wine in coffee cups]

Hi everyone,

New here, seeking a little guidance! I'd really appreciate any advice you all have.

I've been working in economic consulting ever since I graduated from college in 2008. While I am quite happy with my job for the time being, the expectation is generally that we ship out after 3-4 years and go back to school because of the limited advancement opportunities without an MBA or PhD. With this in mind, I'm preparing to apply to stats PhD programs this fall for entry in fall 2011.

I'm looking for statistics PhD programs that would offer faculty and research opportunities with an applied social science focus, specifically in education and economics. There seem to be a number of universities that have interdisciplinary groups bridging statistics and these fields, e.g. Harvard's Institute for Quantitative Social Science and U Washington's Center for Statistics and the Social Sciences. Am I on the right track in thinking that a school with these sorts of groups will offer what I want, or will most of those be directed at students actually in social science departments? I'd really appreciate any suggestions for specific programs that anyone here has to offer. So far I've found this professor at Northwestern who seems like he does a lot of what I want to do, but obviously more options would be great.

I'm not sure how competitive of programs I should be aiming for - here's what I've got:

- white female, US citizen (which I'm told will be help me?)

- B.A. in mathematics in 2008 from a top liberal arts college

- 3.9 GPA overall, close to 4.0 in major

- senior thesis was a group research project related to random walks (but no other academic research experience )

- haven't taken general GRE yet, but only 63rd percentile on GRE math subject test from senior year of college because it had been four years since I last did calculus

- some coursework in statistics: probability theory, mathematical statistics, regression analysis, survey sampling analysis

- some coursework in computer science: introductory CS, data structures

- fairly extensive pure math coursework: calculus sequence, linear algebra, real analysis I & II, abstract algebra I & II, topology, complex analysis, number theory

- lots of experience with SAS (from my job actually), and some experience with R, S-Plus, Stata, Java programming, LaTeX (from college)

Thoughts? (And thanks in advance, of course!)

[hubris]

Are you sure want a statistics degree?

It seems like a program in econometrics would satisfy your requirements (there are more economics programs than stats).

That said your stats look pretty good regardless of your choice.

Just take the power-prep tests and you should be ready to go wrt the GRE general test.

Edited January 11, 2010 by hubris

[kowtown]

I have similar interests, and I too switched from econ to stats, though as an undergrad. I desired the PhD but I took a look at the short-term prospects and decided statistical consulting was better than economic consulting. I also became more interested in statistics itself than economics while taking probability and regression courses in preparation for econometrics. I just finished applying to a mix of master's and PhD programs, so I can offer some recommendations. My background is not as strong as yours but I'll let you know how it turns out. Hopefully the economy is doing better next season because right now it seems that there are very few spots for very many applicants.

Your profile seems nearly ideal. I wouldn't shy away from the top programs, but apply broadly. You have stellar marks in the right math, statistics, and computer science courses. You also have real-world experience working with data sets. A field of application is usually desired, so I'd highlight some of your experiences in economics in your application as well. Definitely brush up on calculus, take some practice tests, and shoot for 80th percentile or better on the subject test. A general test quantitative score near 800 is expected. Even if you can't achieve these, though, the other areas of your application could make up for not-so-stellar test scores. Decide who can write you glowing letters of recommendation and reinitiate contact. At least two of these should be from math or stat professors if possible. (These may also be the best people to ask for advice.)

I wouldn't worry about the lack of research experience too much--a group paper on random walks is better than nothing, and I don't think much meaningful research is done at the undergraduate level anyway. You haven't had sufficient exposure to statistics to decide on an area of research, but definitely do find some areas you're interested in and communicate them to the admissions committees. By this I mean theoretical areas, topics of statistics where you'd be happy developing new theories or methodologies, ideally with applications to the social sciences or similar. Many people choose statistics for the flexibility of applications, but remember you'll be a statistician first. When researching schools click on the faculty research link or the faculty profiles and google/wikipedia anything you're unfamiliar with or that sounds interesting. Bayesians seem to be particularly interested in applications to the social sciences.

Washington and Harvard are very good choices for social science applications, as are Cornell and CMU. Many members of the Cornell faculty have cross-appointments with the Social Statistics department of the ILR School (Industrial and Labor Relations), and the CMU Department of Statistics is housed in the College of Humanities and Social Sciences and prides itself on cross-disciplinary research. Both Larry Hedges and Bruce Spencer are Faculty Fellows at Northwestern's Institute for Policy Research in addition to being professors in the statistics department there. Other departments with members interested in social or behavioral science, education, or policy applications include U Pitt, Wharton (U Penn), Columbia, and George Washington. UC Santa Barbara offers an emphasis in Quantitative Methods in the Social Sciences. I'm sure there are more.

You're at an advantage starting this early. The above are good places to start. The search can be exhausting, but probably worth it in the end. Begin working on your statement of purpose after you've found some areas of interest. You know you're applying to the right school when the "fit" paragraph comes easily. Good luck!

Edited January 18, 2010 by kowtown