Jump to content

(Just another thread about) Picking a Statistics Program


Recommended Posts

Hi all,

 

After the dreadful months of applying/ waiting, the downs of rejections and the ups of acceptances,I've come down to a few schools to pick from: Ohio State, Boston University, and Duke. All are for PhD in Statistics. I've been to BU and Duke for visits. I couldn't attend the Visit Day for OSU but I was in a mini research program there two years ago, so at least I have an idea about the area/ school. I'm not sure whether I'd want to go for academia or industry after graduation yet. Here are my thoughts:

 

Duke: Pretty much what everyone has been telling me to pick. Ranking-wise, it's the best. They give me a very decent financial package, with a semester without responsibilities. My strongest impression during my interview day was that they're very into themselves, and into Bayesian Statistics. This seems to be one of the "negatives" when I hear people talk about Duke, but somehow I wasn't bothered by this. I had a great interview day, enjoyed many of the conversations with the faculty, and there are at least 2-3 faculty there whose research areas I'm interested in. I also like the fact that most students there graduate after an average of four years. My main concern is, should I be worried about this the Bayesian extremity? Will this, in any way, later make it harder for job placement?

 

Ohio State: Again, I couldn't come down for the visit day. Good thing about the dept; quite large, so there will be several choices regarding research areas. I've talked via phone with a few professors there and I enjoyed the vibe I got from it - not necessarily about their own research areas. I've also received the First year fellowship, so that'd be one full year without responsibilities - quite nice. However, a couple people have mentioned to me that as a state school, maybe the funding will not be as stable? I never thought of this before, but I might as well throw it out there to think about.

 

Boston University: I talked to about 5 professors and 2 students there. The visit day was just for me, and I wasn't able to talk to as many prof3essors as I had hoped. I'm very very interested in the work of one professor there, but that's the only one (from the 5 I talked with that day). Pros: Right in Boston, which is my favorite city ever. Close to many other institutions. They also mention a lot about interdisciplinary, and it seems so from all the website digging, but I didn't quite feel as strong about that as what I felt during the Duke visit. Cons: Lowest of all the ranking. They offer me a slightly higher (20% higher compared to Duke) but then of course it's more expensive to live in Boston. I'm not sure whether the fact that there's no separate Math & Stat depts should be considered a pro or a con.

 

 

So for now, I'm slightly leaning more towards Duke because of the higher ranking, great impression from interview days and decent stipend package. I'd really appreciate if you have any other things to chip in. Are there any other great things about OSU/ BU that I missed? Are job placements for one institution significantly better than others? Does anyone know about academia placements for these three?

 

Thank you a lot!

Link to post
Share on other sites

Based off of the way you describe each scenario, It sounds like Duke is the best option because there seems to be the most faculty with whom you are interested in working with, that coupled with the higher ranking leads me to suggest you go with your instinct here and choose Duke...

Link to post
Share on other sites

I'm at BU right now as an undergraduate statistics major. I can answer any questions you may have about the program or the courses (I've taken the PhD sequence of courses already). I also have some knowledge about the research being done here but not too much. 

Link to post
Share on other sites

I will have to disagree with OhioStateStudent here and say that if you are sure that you are into Bayesian, then Duke is the place to go.  They have some very established people working in a wide range of areas and judging from my visit there, they also support their students well.  However, if you are not sure that you want to do Bayesian statistics, Duke may not be the best choice.   In this case, it may be better to go somewhere where you can decide for yourself whether you lean more Bayesian or frequentist instead of being converted from the onset.  Private sector placements look good, but I'm not sure about the academic placements.     

Edited by caffe freddo
Link to post
Share on other sites

I agree with caffe freddo. It depends on whether you loves Bayes. If you don't love it, it might not be the best choice for you. It's important to check the Prof.'s research interests matchs your's or not.

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
×
×
  • Create New...

Important Information

By using this site, you agree to our Terms of Use and Privacy Policy.