Stat PhD at UNC VS PSU VS UMN VS UFL VS Biostat PhD at Upenn

[little white in Stat]

I am considering my potential decision for these statistics&biostatistics PhD program. It is really a hard choice because I don't know these programs in detail, such as reputation, academic placement. I want to engage in statistical research and step into the academic fields in the future.

I am more likely to go to UNC because of its higher reputation (actually, I am not very sure because their ranking shown in USnews is very close.) And they seem to have many professors engaging in machine learning, which is one of the popular topics these days. I am also attracted by its biostatistics department, which ranks Top 5 with many renowned professors in individualized treatment, deep learning and theoretical fields. But in recent years, the rank of statistics department in UNC is not higher than before maybe because of some distinguished professors went to other universities. I am also worried about the correlation between statistics and OR because actually there are two areas in their department.  Actually, I am more interested in UNC because of its connection with its biostat department and stat department at Duke and NCSU and the gold triangle areas.

The statistics departments at UMN and PSU are bigger than UNC. And the research fields are pretty more than UNC. Although they have many distinguished professors, the academic placements may be not better than UNC because I see that more distinguished professors in other Top departments graduated at UNC. The MCMC fields is pretty strong in UFL. And Upenn may be can find potential chance to choose a co-advisor in Wharton. 

 

Really look forward to your suggestions! Thanks! 

[omicrontrabb]

UNC has a very good statistics department, but its strengths are on the probability/theoretical side of statistics. I’m not sure how connected UNC’s stats and biostats departments are. I know at many schools they are basically completely separate.

Don’t obsess too much over the rankings. They do matter, but your advisor is probably the most important part.

If you’re interested in pure statistics research and pursuing an academic career in statistics, don’t go to U Penn for biostats. Their department is decent, but you will have basically no shot at getting a tenure-track job in a good statistics department. Yes, U Penn sounds good because it is an Ivy League school, but those other programs you listed are stronger in statistics.

[Stat Assistant Professor]

It looks like UNC STOR does have some joint faculty who are in UNC Biostatistics: https://stat-or.unc.edu/people/adjunct-and-joint-faculty

Some of the joint faculty from Biostat are pretty well-known (e.g. Ibrahim and Kosorok) and whose work appears in top statistics journals like JASA and Biometrika (not just journals like BMC Bioinformatics, Biostatistics or Statistics in Medicine, which also contain good content but may not be as helpful in getting a job in a Statistics department). So it would probably be fine to go to UNC STOR and have one of those Biostatistics professors as a co-advisor for your thesis.

Besides interacting with those with joint appointments, I'm not sure how much overlap there is between UNC STOR and UNC Biostat there is though -- the coursework is separate, and as a whole, the research emphasis seems to be vastly different between the two departments.

Edited March 6, 2019 by Stat PhD Now Postdoc

[Cavalerius]

From what I gathered, the biostat and stat departments at UNC are now relatively distinct, although it seems that in the past, on the basis of certain comments from professors, the two were more collaborative. The UNC STOR department also appears to have closer connections with Duke than with NCSU. Perhaps this situation is due to Duke being a bit closer geographically and easily reachable by bus, to NCSU being so large that it doesn't really need to associate with anyone else, and to Duke and UNC STOR having somewhat complementary programs (with Duke focusing on Bayesian and computational methods and UNC STOR focusing on probability and stochastic processes).

Edited March 6, 2019 by Cavalerius