Stony Brook Statistics Ph.D Problematic?

[wine in coffee cups]

Wow: only ONE person in the history of TheGradCafe results has been rejected from Stony Brook's AMS program, not just the statistics track. Many (most?) students admitted without funding, based on the comments.

 

Here is this year's common qualifying exam students in AMS take after their first semester: part A (2 hours) part B (1 hour).

 

Here is this year's statistics track qualifying exam taken in the middle of the second year: math stat (2 hours) applied (24 hours).

 

Suffice it to say, some red flags about the quality of the students and the training. I had no idea!

[student12345]

Wow: only ONE person in the history of TheGradCafe results has been rejected from Stony Brook's AMS program, not just the statistics track. Many (most?) students admitted without funding, based on the comments.

Here is this year's common qualifying exam students in AMS take after their first semester: part A (2 hours) part B (1 hour).

Here is this year's statistics track qualifying exam taken in the middle of the second year: math stat (2 hours) applied (24 hours).

Suffice it to say, some red flags about the quality of the students and the training. I had no idea!

Wine, those exams look like something our undergraduates would take here in Boston U. I don't believe that passing these exams determines competency at the Master's level, even.

Edit: Having taken a closer look, it seems like BU freshmen could easily ace that general qual. And sophomores could do the same with the stats exam.

I agree. Red flag.

Edited April 20, 2013 by kimolas

[biostat_prof]

Note that I said that it was the lack of any advanced coursework that was problematic. And while curricula vary, most decent programs offer and require (or very, very strongly suggest) a year of mathematical statistics beyond the usual Casella & Berger-based course for Masters/advanced undergraduate students. A lot of stat departments will also throw in a course or two in measure theory and large sample theory, and biostat places typically require a course on linear models. One of the major reasons to attend a quality stat/biostat program is that the professors there can teach students this material better than most can learn it by themselves. In such programs, "independent reading" is what you do when you're working on your dissertation and need to learn about a special topic that goes beyond the core training. 

 

Well, off the top of my head, Harvard's biostat program only requires one semester of theory, and Berkeley's biostat program has no required courses at all. That said, they certainly offer more advanced courses, and my guess is that most students end up taking the more advanced courses even if they aren't necessarily required. I just quickly eye balled the publication records of their faculty, and while it's certainly not a top-tier department, all of their biostat faculty seem to be publishing. Indeed, all of them seem to have at least some recent methodological papers, even though they generally weren't in the best journals. And at the end of the day that's what's most important for a PhD program. The vast majority of employers won't even ask for a transcript or care which courses you have taken, so the fact that their course offerings are weak is not a major concern in my mind. I certainly wouldn't describe their program as "fraudulent."

 

That said, I would be nervous about enrolling at Stony Brook with the hope of landing a job in finance. I have never heard of any biostat PhD graduates working in finance. That isn't to say that it has never happened, but I think it's safe to say that it's not common. And I have also been told that Wall Street strongly prefers graduates of "name brand" schools because they want to impress clients by saying "our Harvard guys are working on it." I don't know how important that is, but I will say that the people I know who have worked in Wall Street after getting a stat PhD have all been Stanford or Chicago graduates (mostly Stanford). I can't say whether or not Stony Brook is your boyfriend's best option without knowing what his other option is, but I will say that if his other option is offering funding and Stony Brook isn't, he should take the other option, period. As I have noted elsewhere, getting a PhD is a questionable financial decision even with funding, and it is virtually never a good idea without funding. If one were choosing between a top-ranked school with no guaranteed funding but the possibility of finding funding later versus a much lower-ranked school with funding, then maybe, but even then it's a questionable call. I would never turn down a funded offer for a place like Stony Brook.

 

Hope that helps. Feel free to PM me with any other questions.

[WaddleDoos]

Thanks everyone for the input. I will be sending out private messages to get an opinion about the 2nd school.

 

A little about us: I come from a european (irish/english) background while my boyfriend is an international asian who I met during his masters. I feel that I understand American culture better since I grew up here (so for example no advanced phd classes in a phd program is odd) while he feels that he has the know how because it's HIS field.

 

Once again, thanks everyone for helping out and contributing your opinions. It's been very helpful. I'll be relying on your advice and input regarding the private message. Thanks again.

 

EDIT: (Some responses to comments)

 

My bf has this idea in his head that he can make a lot more money if he ran into marketing/finance/banking, etc. I personally feel that going to SB is #1 not going to guarantee such a job, and #2 you wouldn't necessarily make gigantic amounts of cash anyway over statistics/biostats?

 

I suppose it's safe to say he "changed his mind" because he saw dollar signs and feels that a ph.d with stony brook's name on it is enough, even if the courses are lower tier or through "directed reading".

Edited April 21, 2013 by WaddleDoos

[Tronathan]

Wine, those exams look like something our undergraduates would take here in Boston U. I don't believe that passing these exams determines competency at the Master's level, even.

Edit: Having taken a closer look, it seems like BU freshmen could easily ace that general qual. And sophomores could do the same with the stats exam.

I agree. Red flag.

 

The math stat exam has typical questions you would find in the homework of the Casella & Berger book. I highly doubt Boston or any university has lower division undergraduate courses available that would prepare a sophomore to ace that test.

 

Also, NRC has Stony Brook ranked 16th in applied math, between Cal Tech and Georgia Tech.

[student12345]

The math stat exam has typical questions you would find in the homework of the Casella & Berger book. I highly doubt Boston or any university has lower division undergraduate courses available that would prepare a sophomore to ace that test.   Also, NRC has Stony Brook ranked 16th in applied math, between Cal Tech and Georgia Tech.

I believe it is not too uncommon to see mathematical statistics taught with Casella/Berger in undergraduate programs. UCSD may be one such program, based on what I saw when I visited. It is a good introduction to statistics, but there are certainly books with the required about of mathematical rigor for research that are not seen until graduate-level programs, such as Lehmann. Although the statistics program is in the applied mathematics department, it is not quite at the level that the rest of the department would appear to be at, based on the NRC rankings.

[cyberwulf]

I believe it is not too uncommon to see mathematical statistics taught with Casella/Berger in undergraduate programs. UCSD may be one such program, based on what I saw when I visited. It is a good introduction to statistics, but there are certainly books with the required about of mathematical rigor for research that are not seen until graduate-level programs, such as Lehmann. Although the statistics program is in the applied mathematics department, it is not quite at the level that the rest of the department would appear to be at, based on the NRC rankings.

 

One can teach from Casella & Berger at many levels of rigor. Most undergraduate courses taught out of C&B cover the elementary concepts but leave out some of the more advanced material or give it only a cursory treatment.

 

I would consider the linked PhD math stat exam to be at the level of a standard first-year Masters exams at a top biostat department. I have trouble believing that advanced undergrads anywhere would find it easy, never mind sophomores!

[student12345]

One can teach from Casella & Berger at many levels of rigor. Most undergraduate courses taught out of C&B cover the elementary concepts but leave out some of the more advanced material or give it only a cursory treatment.   I would consider the linked PhD math stat exam to be at the level of a standard first-year Masters exams at a top biostat department. I have trouble believing that advanced undergrads anywhere would find it easy, never mind sophomores!

I don't see any particular reason for that. The only prerequisite for the full treatment of Casella is an introductory probability course (which some freshmen take here). As a sophomore having done the full Casella + some of Lehmann, I can say with confidence that there was no point where I felt my background was lacking.

[wine in coffee cups]

I would consider the linked PhD math stat exam to be at the level of a standard first-year Masters exams at a top biostat department. I have trouble believing that advanced undergrads anywhere would find it easy, never mind sophomores!

You really don't think there is a big gap in the difficulty of that qual vs. the first years master's exam taken at, say, UW bio/stat? Because I sure as hell wouldn't mind taking the Stony Brook qual instead of the UW's!

[sisyphus1]

You really don't think there is a big gap in the difficulty of that qual vs. the first years master's exam taken at, say, UW bio/stat? Because I sure as hell wouldn't mind taking the Stony Brook qual instead of the UW's!

 

I think there is a gap, but not a huge one. I have a master's in stats, and the questions are not too different from questions on some of the final exams of the more difficult classes.