PhD: BU STAT vs UMN BIOSTAT

[willhere]

 

Hi everyone,

My undergraduate major is STAT. And I really want to learn something in PhD training. Up to now, I only received two STAT/BIOSTAT PhD offers and am really confused about them. My research field is not that clear because I will not be supervised to do a typical statistics paper before graduation. I am not sure how well I could do so I am not sure I could go to academia or industry. But if I do well in academics, I prefer to being a professor.

 

BU:

Pros:

1. Boston is a big city so it is better to live there than Minnesota. 

2. It is Statistics. It has wider applications and it is easier to shift into another area than Biostatistics.

3. They are some professors researching in Bayesian Statistics and Network Science, which seems to be two potential research areas for me.

Cons:

There is no ranking in USNEWS for it. I do not know this program's reputation. I did not find where the graduate students go after finishing this program.

UMN:

Pros:

It ranks 24 in USNEWS. I have heard it is a program with a good reputation.

Cons:

1. I have checked the research fields of professors there but find no professors focusing on network science. There are some doing Bayesian statistics and machine learning.

2. One of my friends graduated from UMN said Minnesota is so cold and boring...

3. It is biostatistics so it seems to narrow me down in this field.

 

I have confidence in finishing the PhD training in either school. However, since my research area is not settled and I am not sure about academia or industry, I really need your advice! Thank you very much!

Edited March 7, 2019 by willhere

[StuartLittle]

First off, congratulations to your acceptance! Based on what you wrote, I would say that BU is a better choice. Search up the names of the professors and see where they come from, their reputation and their research.

 

Also having a degree in BU and a professional network in Boston is much more advantageous because Boston has A LOT of consulting companies AND also a lot of large hospitals and research center that allows you to do biostatistical research if you want to.

[Geococcyx]

I'm guessing you're mainly looking to work with Dr. Kolaczyk at BU?  He seems like a pretty good fit for your interests, and he's got recent publications in JASA and AAS (and the Journal of Machine Learning Research, which I think is also pretty good?), so I think you'd probably be in OK shape if you were working with him.  I'd generally be concerned about trying to go into academia from an unranked program, but I'm guessing our more experienced posters would confirm that Dr. Kolaczyk has a sufficient background and publishing record to get you into a decent postdoc if you excelled.  

That said, Minnesota may necessitate more driving to get to things you're interested in, but I do kinda doubt that you wouldn't find things you'd be interested in there -- you do have a 3 million person metro area to work with, after all.  If Minnesota's visit day hasn't happened yet, you may want to go and ask the students about whatever your interests are.  I'm sorry for your friend, but unless y'all share a lot of interests that require warm weather and salt water, then I don't think you'd end up missing out on too much if you go there.  

[Stat Assistant Professor]

Boston University doesn't have a separate statistics department; its Mathematics & Statistics PhD programs are both under the Mathematics department. So the rankings for BU would probably be under Mathematics rather than Statistics. 

To the OP: what are your interests? Are you more interested in mathematical/theoretical stuff or more applied (e.g. in clinical trials, medical imaging, meta-analysis, etc.)? If the former, BU would probably be a better fit than UMN, although I am sure you could find at least a couple faculty at UMN Biostatistics who do some research on more mathematical statistics as well. But if your interests are mainly applied, then UMN is better probably.

[SoymilkLatte]

I would strongly vote for BU.

1. The former head of the UMN biostat division, also the one having great reputation on Bayesian analysis, Brad Carlin, was laid off (officially as 'retired', interesting) because of sexual harassment. Meanwhile, there are several elder professors are likely to retire in a few years, and a substantial part of the young faculties does not seem having very strong academic reputation/publications compared with other top programs.The ranking of the program will possibly be decreasing in the future. 

2. Considering your interest, I'm pretty sure that UMN biostat does not have professor working on network science. There are one or two doing machine learning previously, but none of them mainly focusing on machine learning and deep learning for now. Most of the professors are focusing on the traditional 'biostat' fields. Stat department is always a better place if you are interested in those hot topics. 

3. Biostat would definitely narrow you down in job hunting. Most of the HR people in IT/finance company would treat you as someone from biological background. You have to make more effort on persuading them that you are also good at statistics and can do the same thing as a stat phd. So why not just get a stat phd?

4. Personally, I think most of the people would prefer the weather in Boston. Minnesota is indeed too cold and boring. Half-year winter from Oct to May? 10 inches of snow in 3 hrs? Absolutely no good seafood? Remember, Phd is a 5-year or more commitment, make sure you choose somewhere you really want to go!

 

---- From someone graduated from UMN biostat. 

Edited March 8, 2019 by SoymilkLatte

[willhere]

On 3/7/2019 at 5:00 PM, StuartLittle said:

First off, congratulations to your acceptance! Based on what you wrote, I would say that BU is a better choice. Search up the names of the professors and see where they come from, their reputation and their research.

 

Also having a degree in BU and a professional network in Boston is much more advantageous because Boston has A LOT of consulting companies AND also a lot of large hospitals and research center that allows you to do biostatistical research if you want to.

Thank you for your comments! I have paid a campus visit there and find 90% of the stat PhD students go to industry. I have no doubt that Boston is a nice place. However, considering two big names on the opposite side, will it make disadvantages to BU students?

[willhere]

On 3/8/2019 at 1:30 AM, Geococcyx said:

I'm guessing you're mainly looking to work with Dr. Kolaczyk at BU?  He seems like a pretty good fit for your interests, and he's got recent publications in JASA and AAS (and the Journal of Machine Learning Research, which I think is also pretty good?), so I think you'd probably be in OK shape if you were working with him.  I'd generally be concerned about trying to go into academia from an unranked program, but I'm guessing our more experienced posters would confirm that Dr. Kolaczyk has a sufficient background and publishing record to get you into a decent postdoc if you excelled.  

That said, Minnesota may necessitate more driving to get to things you're interested in, but I do kinda doubt that you wouldn't find things you'd be interested in there -- you do have a 3 million person metro area to work with, after all.  If Minnesota's visit day hasn't happened yet, you may want to go and ask the students about whatever your interests are.  I'm sorry for your friend, but unless y'all share a lot of interests that require warm weather and salt water, then I don't think you'd end up missing out on too much if you go there.  

When I paid a visit to BU, another professor there said that there are not that many things happening in network analysis. And Dr. Kolaczyk seems to be working with Geometry professors so that I am a little bit afraid because I did not study geometry. When I looked into UMN biostat professors' research interests, I do not feel that excited. Maybe I did not look into their papers carefully.

I see UMN biostat graduates have a very impressive academic placement: 2 FSU stat AP without Postdoc and 1 JHU biostat with Postdoc. I chatted with some current students and they said that I would find something interesting there after the first year coursework, more familiar with UMN. 

There is another option, that is UW Biostat Capstone - 18-month program aiming at job hunting. I would like to treat it as the stepstone to apply for Stat PhD programs. But this is their first year and the director said this program is at disadvantage for further study compared with their 24-month Thesis program. In the last year, two Thesis students successfully transferred to UW biostat PhD program. Another two went to UBC and Pittsburgh Stat PhD program.

I am not sure whether I could go to a Stat PhD program like UCLA or PSU after finishing study there.

Many thanks! 

[willhere]

On 3/8/2019 at 2:36 AM, Stat PhD Now Postdoc said:

Boston University doesn't have a separate statistics department; its Mathematics & Statistics PhD programs are both under the Mathematics department. So the rankings for BU would probably be under Mathematics rather than Statistics. 

To the OP: what are your interests? Are you more interested in mathematical/theoretical stuff or more applied (e.g. in clinical trials, medical imaging, meta-analysis, etc.)? If the former, BU would probably be a better fit than UMN, although I am sure you could find at least a couple faculty at UMN Biostatistics who do some research on more mathematical statistics as well. But if your interests are mainly applied, then UMN is better probably.

My current interests are network analysis and might be high-dimension data and Bayesian statistics. I admit that I lack enough exposure to all stat fields. I am not that interested in clinical trials but I think big health data is interesting. I would like to do more methodological things rather than applied. 

I see there are some professors doing network analysis in UW biostat. If I go there, I want to work with them. But I am not sure what kind of stat PhD I could get because my undergraduate school is not famous.

Would you mind offering some suggestions? Thank you!

[willhere]

On 3/8/2019 at 8:10 AM, SoymilkLatte said:

I would strongly vote for BU.

1. The former head of the UMN biostat division, also the one having great reputation on Bayesian analysis, Brad Carlin, was laid off (officially as 'retired', interesting) because of sexual harassment. Meanwhile, there are several elder professors are likely to retire in a few years, and a substantial part of the young faculties does not seem having very strong academic reputation/publications compared with other top programs.The ranking of the program will possibly be decreasing in the future. 

2. Considering your interest, I'm pretty sure that UMN biostat does not have professor working on network science. There are one or two doing machine learning previously, but none of them mainly focusing on machine learning and deep learning for now. Most of the professors are focusing on the traditional 'biostat' fields. Stat department is always a better place if you are interested in those hot topics. 

3. Biostat would definitely narrow you down in job hunting. Most of the HR people in IT/finance company would treat you as someone from biological background. You have to make more effort on persuading them that you are also good at statistics and can do the same thing as a stat phd. So why not just get a stat phd?

4. Personally, I think most of the people would prefer the weather in Boston. Minnesota is indeed too cold and boring. Half-year winter from Oct to May? 10 inches of snow in 3 hrs? Absolutely no good seafood? Remember, Phd is a 5-year or more commitment, make sure you choose somewhere you really want to go!

 

---- From someone graduated from UMN biostat. 

Thank you for your honest sharing!

1. That is the case but I do not know how bad this program will be.

2. Definitely, there are not professors in network analysis but some are in ML like Prof Wei Pan? I think big health data is interesting but I am not a fan of clinical trials.

3. That is true. But first I want to try to figure out whether I do well in academics. If not, I want to go to IT. Given this, I feel BU is not that reputable than UMN?

4. I agree. I just thought about whether I could suffer from this in order to go to a more reputable program.

Now I think this is really a hard decision. How do you think about UW biostat MS capstone as a stepstone to a better stat PhD program?

[willhere]

Recently, I received Biostat PhD offer from the Ohio State University and Ms. Capstone admission from the University of Washington. It makes me feel harder to decide... Thank you for your help!

[Stat Assistant Professor]

4 hours ago, willhere said:

My current interests are network analysis and might be high-dimension data and Bayesian statistics. I admit that I lack enough exposure to all stat fields. I am not that interested in clinical trials but I think big health data is interesting. I would like to do more methodological things rather than applied. 

I see there are some professors doing network analysis in UW biostat. If I go there, I want to work with them. But I am not sure what kind of stat PhD I could get because my undergraduate school is not famous.

Would you mind offering some suggestions? Thank you!

UW Biostat is certainly a very prestigious program, but is this capstone program fully funded? If it is not funded, then I am not sure if it is worth going into debt to use it as a stepping stone for PhD programs in the future when you already have three funded PhD offers. While a Masters from UW could very well help you get into more prestigious programs, I wouldn't say that BU, UMN, or OSU are so non-reputable that it is worth forgoing a funded offer from one of them in hopes of a "better" one in the future -- if your only admissions were to Applied Statistics PhD programs in regional/directional universities, I might consider the Masters option, but your current choices are not bad. If you want to 'move up' in academia or change your research direction, you can always perform well in your doctoral program and switch to something else during your postdoc. If you're aiming for industry, I don't think the school (BU vs. UMN vs. OSU vs. UW) will matter that much, although UW's location in Seattle might be slightly more helpful in getting data science jobs at big companies headquartered there.

[SoymilkLatte]

4 hours ago, willhere said:

Thank you for your honest sharing!

1. That is the case but I do not know how bad this program will be.

2. Definitely, there are not professors in network analysis but some are in ML like Prof Wei Pan? I think big health data is interesting but I am not a fan of clinical trials.

3. That is true. But first I want to try to figure out whether I do well in academics. If not, I want to go to IT. Given this, I feel BU is not that reputable than UMN?

4. I agree. I just thought about whether I could suffer from this in order to go to a more reputable program.

Now I think this is really a hard decision. How do you think about UW biostat MS capstone as a stepstone to a better stat PhD program?

1. The fact that UMN Biostat may not be as strong as the current ranking shows matters if the ranking is one of the most important part for your consideration.

2. Dr. Pan is advising several students in Biostat department and also a few (>=3, I'm not sure) students from Stat & ECE now (usually the students from Stat/ECE have more solid background when doing ML/DL, probably the reason why he prefer them?). I doubt if he has enough funding to support more people working on his ML project. Given he is probably the only one who is seriously doing ML stuff in the department, if you could not get along with his style, your situation might be a little bit awkward. I'm not familiar with him personally, but I heard he is more to the pushy side. Do not put all your eggs in one basket. I guess you could find more professors from BU stat/math interested in ML.

3. I do not think BU is less reputable than UMN, at all. Considering alumni network, I would say that BU is a little bit more recognized during job hunting compared with UMN. However, going to industry, once you've gone through the initial HR screening, the brand/ranking of your university would be no longer a big deal. 

4. Enjoying yourself in your daily life is one of the most important part to live a happy, healthy and successful PhD life without depression (which affect 60% of the phd students here in the U.S.). You do not know what it means when you are saying 'suffer' with ease now. 

If what you really want is a Stat PhD, starting a biostat PhD may not be a wise choice. UW is definitely a *big* name in Biostat area. If you don't mind to fund yourself, I would say it could be a great stepping stone to a better Stat/Biostat PhD program. If you are still hesitating on going to academia or industry, it also could be a period of time for you to figure it out with plenty of room to plan your next move. None of the choice is 100% perfect and can ensure 100% success in your future. You'll gain something and at the same time lose something, but everything'll be worth it in the end. We cannot make the decision for you here, just follow your heart.

[willhere]

13 hours ago, Stat PhD Now Postdoc said:

UW Biostat is certainly a very prestigious program, but is this capstone program fully funded? If it is not funded, then I am not sure if it is worth going into debt to use it as a stepping stone for PhD programs in the future when you already have three funded PhD offers. While a Masters from UW could very well help you get into more prestigious programs, I wouldn't say that BU, UMN, or OSU are so non-reputable that it is worth forgoing a funded offer from one of them in hopes of a "better" one in the future -- if your only admissions were to Applied Statistics PhD programs in regional/directional universities, I might consider the Masters option, but your current choices are not bad. If you want to 'move up' in academia or change your research direction, you can always perform well in your doctoral program and switch to something else during your postdoc. If you're aiming for industry, I don't think the school (BU vs. UMN vs. OSU vs. UW) will matter that much, although UW's location in Seattle might be slightly more helpful in getting data science jobs at big companies headquartered there.

Yes, you are right. There is no funding for the 18-month UW Capstone program. It is designed for job hunting so students will not be requested to take STAT 512\513, which is the core courses for 24-month Thesis program. I think it is a disadvantage. I do not feel the fund is a very big point but the time and its output. Based on your experience, do you think there are some professors in BU are strong enough could place their students to top posdoc? I did not find some on their websites.

[willhere]

13 hours ago, SoymilkLatte said:

1. The fact that UMN Biostat may not be as strong as the current ranking shows matters if the ranking is one of the most important part for your consideration.

2. Dr. Pan is advising several students in Biostat department and also a few (>=3, I'm not sure) students from Stat & ECE now (usually the students from Stat/ECE have more solid background when doing ML/DL, probably the reason why he prefer them?). I doubt if he has enough funding to support more people working on his ML project. Given he is probably the only one who is seriously doing ML stuff in the department, if you could not get along with his style, your situation might be a little bit awkward. I'm not familiar with him personally, but I heard he is more to the pushy side. Do not put all your eggs in one basket. I guess you could find more professors from BU stat/math interested in ML.

3. I do not think BU is less reputable than UMN, at all. Considering alumni network, I would say that BU is a little bit more recognized during job hunting compared with UMN. However, going to industry, once you've gone through the initial HR screening, the brand/ranking of your university would be no longer a big deal. 

4. Enjoying yourself in your daily life is one of the most important part to live a happy, healthy and successful PhD life without depression (which affect 60% of the phd students here in the U.S.). You do not know what it means when you are saying 'suffer' with ease now. 

If what you really want is a Stat PhD, starting a biostat PhD may not be a wise choice. UW is definitely a *big* name in Biostat area. If you don't mind to fund yourself, I would say it could be a great stepping stone to a better Stat/Biostat PhD program. If you are still hesitating on going to academia or industry, it also could be a period of time for you to figure it out with plenty of room to plan your next move. None of the choice is 100% perfect and can ensure 100% success in your future. You'll gain something and at the same time lose something, but everything'll be worth it in the end. We cannot make the decision for you here, just follow your heart.

Thank you, bro! I do feel the limitation of research in UMN. I am looking into OSU interdisciplinary biostat program, which the first two-year coursework are the same to OSU stat. I could choose professors from stat as dissertation advisors. From the list https://biostatprograms.osu.edu/biostatphd/faculty, half of the stat faculty are there. Compared to UMN, OSU allows for more interactions with the stat, which I prefer. However, this program does not have a ranking and I guess some professors' background is not as strong as UMN and even BU. BU professors' education background are all reputable schools. How would you value this OSU program?

[Stat Assistant Professor]

8 hours ago, willhere said:

Yes, you are right. There is no funding for the 18-month UW Capstone program. It is designed for job hunting so students will not be requested to take STAT 512\513, which is the core courses for 24-month Thesis program. I think it is a disadvantage. I do not feel the fund is a very big point but the time and its output. Based on your experience, do you think there are some professors in BU are strong enough could place their students to top posdoc? I did not find some on their websites.

I saw that BU has just hired Yves Atchades as full professor, and he is a very strong researcher. If you were to go to BU and were co-supervised by Atchades and Luis Carvalho (say) *and* wrote two good papers as part of your PhD, then I would say you have a decent shot at a top postdoc. You could possibly get a top postdoc at a school like Duke in that case.

Edited April 11, 2019 by Stat PhD Now Postdoc

[SoymilkLatte]

9 hours ago, willhere said:

 Thank you, bro! I do feel the limitation of research in UMN. I am looking into OSU interdisciplinary biostat program, which the first two-year coursework are the same to OSU stat. I could choose professors from stat as dissertation advisors. From the list https://biostatprograms.osu.edu/biostatphd/faculty, half of the stat faculty are there. Compared to UMN, OSU allows for more interactions with the stat, which I prefer. However, this program does not have a ranking and I guess some professors' background is not as strong as UMN and even BU. BU professors' education background are all reputable schools. How would you value this OSU program?

I've heard some good comments toward OSU stat department. To me, the OSU faculties are having decent background, do not seem weaker than UMN and BU. I would suggest you looking through your POI's previous work, not their education background. A good researcher is not defined by his/her graduated school. People do most of their valuable works during PhD, not undergrad (which decides their PhD school).

A few faculties with less publication cannot say a thing on the program's quality. You'll not be advised by all of the professors, and there's not a single department can be perfect and filled with top faculties. In addition, I would not worry too much about the program ranking. Again, people will value you by your work and publication, not the brand of your school. 

Always go to somewhere fits better instead of pursuing higher ranked program. I would say, the OSU program is a great choice, while you have to decide whether it's a good fit for you. 

Edited April 11, 2019 by SoymilkLatte