Top 2 Biostat vs. Top 10 Stat PhD

[statprospect]

Hi everyone. I have two very good offers for PhD programs, one from a top 2 biostat department, the other from a top 10 statistics department (most people would probably say in the 5-8 range). I am trying to weigh the pros and cons of choosing one over the other and was hoping that you could shed some light on the problem.

The offers are materially the same in total (though biostat is an RA while stat is a TA), although even if they were different I would not be so concerned about it. I am really wondering more about whether or not I would be limited in terms of career choices, especially in academia, if I chose the biostat program. I prefer the location of the biostat program, but probably wouldn't suffer in either place. In terms of coursework, the biostat program is probably a bit more targeted towards applications, but it is flexible enough that I could (and would) be able to take the standard theory courses that I would have in a pure stat program.

In terms of my research interests, I love statistics. If I had to choose an area of application, which is something that I think would be important for me to do even if I ended up doing research in theory and methods, it would probably be biostatistics. With that said, I am a very intellectually curious person, so I am sure that I would probably enjoy other applications as well.

Thoughts? Thanks for the help!

[greenparker]

I would definitely go for the stat program, especially since you are not closed to other areas of research. All the schools in the top 10 are almost at the same level, except maybe Berkeley and Stanford. And if you dont mind the city, stats is the way to go. Good luck.

[sparkplug]

What is the RA offer? Residential advisorship? Sounds like less stress but not as interesting as a TA-ship.

Career wise, stats PhDs can switch to doing biostatistics fairly easily, but if you are just focusing on biostats to begin with, it might not be easy to switch to another field of stats. I can't speak to academia though.

[statprospect]

An RA offer is a research assistantship appointment.

[sparkplug]

Oh. Haha. I thought it didn't make sense. My mistake.

[mathgirl28]

I had a friend who graduated from Harvard's Biostatistics program and got more statistics faculty offers than biostatistics programs upon finishing. His research however was more theoretical than most in his cohort however (it happened to his friend as well though). In the end he accepted a biostatistics faculty position at Harvard which is where he is teaching now.

All this is to say i think you should select the program where you will get the best (theoretical) training and have the best advisors. Where and how you publish will ultimately decide where you will get offers rather than the name of the school you went to. Your advisor support will also help a lot.

My two cents.

p.s. i am currently in a similar situation and deciding between two great programs, so congrats!

[statprospect]

I had a friend who graduated from Harvard's Biostatistics program and got more statistics faculty offers than biostatistics programs upon finishing. His research however was more theoretical than most in his cohort however (it happened to his friend as well though). In the end he accepted a biostatistics faculty position at Harvard which is where he is teaching now.

All this is to say i think you should select the program where you will get the best (theoretical) training and have the best advisors. Where and how you publish will ultimately decide where you will get offers rather than the name of the school you went to. Your advisor support will also help a lot.

My two cents.

p.s. i am currently in a similar situation and deciding between two great programs, so congrats!

Thank you and congratulations to you as well mathgirl! Are you also deciding between a stats and biostat program? This is a tough call for me since at the biostat program, there is a lot of opportunity to take classes in that university's stats department - they actually take the same core and quals. There are also many students in biostat there who have statistics professors as advisors. I think that the difference is that the statistics department I was admitted to could be said to be generally more theoretical in terms of the research interests of most professors. I would presume that this has some impact on the type of students I would be studying with, which I am not sure is something I should consider. There may be something to be said for having more theory oriented peers going through classes with you.

It has been a bit difficult to pin down what the general feeling is on this issue among faculty at my current institution. Most professors seem to agree with you, but a handful, including the director of graduate studies here, seemed to feel that it would be much more difficult for someone with a biostats degree to get an offer at a statistics department unless he had a really outstanding cv.

I feel like I am trying to decide whether to eat a very delicious apple or a very delicious orange. This is in some ways an unreasonable question to ask other people, since the most reasonable response would be for others to just ask me which I like better. To butcher the metaphor further (sorry), they could both go into a very delicious fruit salad (i.e. help me get to where I want to be), so the question ultimately boils down to which fruit salad customers like best and is most marketable.

[cyberwulf]

Where and how you publish will ultimately decide where you will get offers rather than the name of the school you went to.

This is absolutely spot-on. The difference between stats and biostats departments is:

- In good (eg. top 15) stat departments, there are a handful of faculty whose work would set you up nicely for a career in biostatistics. The remainder work on stuff that will set you up for a career in theoretical statistics research.

- In good (eg.top 6-8) biostat departments, there are a handful of faculty whose work would set you up nicely for a career in theoretical statistics. The remainder work on stuff that will set you up for a career in biostatistical research.

The bottom line is that you can *generally* find someone to do a more applied dissertation with in a good stat department, and the same holds true for theoretical work in a good biostat department.

From the details you've provided, it sounds like you're considering UW-Seattle. If that's indeed the case, it seems like it would be a great choice for you, given the close connections between stat and biostat there. Between the two departments, there are something like 100 faculty, so you will definitely not lack options when it comes time to identifying an advisor and suitable dissertation topic.

Edited February 23, 2012 by cyberwulf

[mathgirl28]

Hey,

I got into a top 10 biostat, top 10 stat, and top 10 CS program. Its weird that i had such a diverse application process, but my interests lie somewhere in the intersection of those 3 program (machine learning-ish/ bioinformatics... but more ML). So while i am extremely happy, i have to make the choice between these, and mine will be for the most part based on the advisor i would have at each of the institutions (which has as much to do with fit as it does prestige/clout of the advisor). That at least was the advise i received so far about how to base my decision.

I have heard a lot about UW-Seattle and it is quite theoretical (which is a good thing). I dont know what stat program you got into, but UW is quite tough Ive heard. That said, look at who would be a good advisor at each of the places and try to let that influence your decision

[caffe freddo]

Hi,

 

Sorry to bump an old thread, but I'm in a similar predicament as well.  I also got an offer from arguably the top biostats PhD program but have another offer from a second tier stats PhD programs that is strong for interdisciplinary work.  I'm generally interested in biological applications, so in that sense both would be a good fit, but I would maybe like to explore other areas as well.  The recent academic placements are arguably better at the stats school, but it is hard to say whether this trend would continue.  However, the biostats program seems to have stronger private sector placement.  I am having a tough time deciding, so I would greatly appreciate hearing everyone's thoughts. 

[ilovefish]

Hi.

 

I think you should choose the Biostat Program if the program is UW, Harvard or JHU. These departments have a bunch of very good faculty members doing theoretical work. Also the application area of these department is very wide. Good luck!

[clamofee]

Hi,

 

Sorry to bump an old thread, but I'm in a similar predicament as well.  I also got an offer from arguably the top biostats PhD program but have another offer from a second tier stats PhD programs that is strong for interdisciplinary work.  I'm generally interested in biological applications, so in that sense both would be a good fit, but I would maybe like to explore other areas as well.  The recent academic placements are arguably better at the stats school, but it is hard to say whether this trend would continue.  However, the biostats program seems to have stronger private sector placement.  I am having a tough time deciding, so I would greatly appreciate hearing everyone's thoughts. 

 

From what I've seen the top Biostats programs have stronger academia than industry placements, so naturally I'm curious which Biostats program this is. Mind sharing/PM me?

 

I've heard that if you're interested in academia, theoretical will help more; if industry, applications will help more. If you know your goals it'll help in the decision process.

[health_quant]

Hi,

 

Sorry to bump an old thread, but I'm in a similar predicament as well.  I also got an offer from arguably the top biostats PhD program but have another offer from a second tier stats PhD programs that is strong for interdisciplinary work.  I'm generally interested in biological applications, so in that sense both would be a good fit, but I would maybe like to explore other areas as well.  The recent academic placements are arguably better at the stats school, but it is hard to say whether this trend would continue.  However, the biostats program seems to have stronger private sector placement.  I am having a tough time deciding, so I would greatly appreciate hearing everyone's thoughts. 

 

I think you and I are in similar boats this year, and maybe even the exact same boat.   (I am assuming that by second-tier stats program, you are still referring to a top 10 or top 15 stats program, as tiers on gradcafe seem to be used to distinguish between programs within that upper echelon.)

 

I think that what earlier posters have noted about academic job placements (i.e., publications outweighing school names) really is the most important factor to consider if you want to go the academic route yourself down the road. The top biostats programs seem to do consistently well in preparing their students in this way (though biostat_prof has noted a general tightening in the job market), and if the stats program has had good placement recently, then I assume they've been supporting students well in this respect, too. Of course, any success has a lot to do with the students themselves and their relationships with advisers.

 

Regarding private sector employment, I imagine that the relative importance of name and program-type will depend on the industry. If it's a highly statistical position, then I imagine that your hiring will be done by other statisticians, or at least people with an awareness of the general strength of stats/biostats programs. In this case, I feel like a candidate who would be competitive for an academic position would also be quite competitive for the private sector.

I suppose if the private sector job really emphasizes applied, collaborative research, then a strong history of that may be quite helpful.

 

April 15 is loooooming. I hope you're having an easier time deciding than I am.