Stat PhD: UIUC vs Iowa State vs Purdue for Spatial/Bayesian

[data_scrub]

As of yesterday I've heard back from all of the schools I applied to, and now I'm trying to decide where to go! I'm interested in doing research in Spatio-temporal stats as well as Bayesian stats (seems to be some amount of overlap between the two), so am looking into advisors with experience in those areas. I'm open to other research areas as well, as I'm sure my interests will change as I get more involved in the field.

By the rankings Iowa State seems to have an edge over the others, but it seems like the research fit is still most important. I know Mark Kaiser is there, but not entirely sure who all in the department does Spatial/Bayes research. UIUC seems to have a few potential advisors I'd like to work with including Bo Li and Xiaofeng Shao. I have heard some negative past student perspectives from Purdue, but working with Vinayak Rao would be interesting considering my research interests are a near match and he recently finished a post-doc at Duke with Gelfand.

As of  now, I'm feeling best about Iowa State and UIUC. I'll be visiting all of these programs in the next few weeks, and would love to hear any opinions or advice on choosing between these schools. I would have TA funding at any of these programs.

I've also been accepted to OSU, but after visiting I'm not so sure about the research fit (and personal fit, I'd much prefer to be in a smaller college town) as well as their relative lack of solid academic placements in recent years. Still, I really liked the people there as well as the other prospective students at the visit day!

[Geococcyx]

Just because I'm a contrarian, I'll say that Nate's presentation at the Ohio State visit's poster session was on spatial statistics, and that the program is generally pretty Bayesian.  I definitely get being overwhelmed by Ohio State's sheer size (and Columbus is pretty big too), but I guess I'd be a little more positive about their research fit for you than you are, in case you are interested in staying in Ohio.  I have way different interests, though, so I'm guessing your concerns are more on the level of individual professors' research than my super blanket-y assessment.

As you've likely seen, Stat PhD Now Postdoc seems pretty positive about Xiaofeng Shao's research, and looking at where he's publishing I really have to agree that he seems great.  I'm having a hard time doing Iowa State justice from a cursory google search, but it seems like Philip Dixon does some spatial statistics, and spatiotemporal statistics might be a good fit for working with a visualization-focused professor like Heike Hofmann (these both had AAS publications that I saw, but they don't quite have the JASA/JRSS-B profile Shao has).

Something that might be useful:  how much smaller of a college town would you like?  Ames is 60-70K, Urbana-Champaign comes out closer to 200K by urban area (although I have no idea how dense it is in the middle).  If you wanted to go somewhere bigger, Des Moines is 600K or so and fairly close to Ames, while Chicago's more like a 2/2.5 hour drive from UIUC but is obviously gigantic (plus Indianapolis is also a 2 hour drive).  What are you looking for?  If you have interests that might involve national tours (e.g. musicals, major comedy shows, attending major professional sports), then I'd suggest that Illinois would be a better fit, but it's hard to prescribe that.  In fact, it might help to know what factors beyond sheer research prominence are most important to you -- do these programs have similar times to degree?  Does one have a really tough qualifying exam that you might worry about?

[data_scrub]

26 minutes ago, Geococcyx said:

Just because I'm a contrarian, I'll say that Nate's presentation at the Ohio State visit's poster session was on spatial statistics, and that the program is generally pretty Bayesian.  I definitely get being overwhelmed by Ohio State's sheer size (and Columbus is pretty big too), but I guess I'd be a little more positive about their research fit for you than you are, in case you are interested in staying in Ohio.  I have way different interests, though, so I'm guessing your concerns are more on the level of individual professors' research than my super blanket-y assessment.

As you've likely seen, Stat PhD Now Postdoc seems pretty positive about Xiaofeng Shao's research, and looking at where he's publishing I really have to agree that he seems great.  I'm having a hard time doing Iowa State justice from a cursory google search, but it seems like Philip Dixon does some spatial statistics, and spatiotemporal statistics might be a good fit for working with a visualization-focused professor like Heike Hofmann (these both had AAS publications that I saw, but they don't quite have the JASA/JRSS-B profile Shao has).

Something that might be useful:  how much smaller of a college town would you like?  Ames is 60-70K, Urbana-Champaign comes out closer to 200K by urban area (although I have no idea how dense it is in the middle).  If you wanted to go somewhere bigger, Des Moines is 600K or so and fairly close to Ames, while Chicago's more like a 2/2.5 hour drive from UIUC but is obviously gigantic (plus Indianapolis is also a 2 hour drive).  What are you looking for?  If you have interests that might involve national tours (e.g. musicals, major comedy shows, attending major professional sports), then I'd suggest that Illinois would be a better fit, but it's hard to prescribe that.  In fact, it might help to know what factors beyond sheer research prominence are most important to you -- do these programs have similar times to degree?  Does one have a really tough qualifying exam that you might worry about?

 

You're right about Nate's poster, Dr. Craigmile does do Spatial research. I'm mainly concerned that Dr. Calder is leaving OSU, as I was even more interested in her research and applications. You make a good point about visualization focused profs, as that's an interest of mine as well. I'll need to dive further into ISU's directory before the visit day.

I'm not too concerned about living by a big city, as far as my hobbies go I'm more outdoor oriented ? That being said the music scene in Chicago is pretty good... Thanks for asking some good questions to follow up on!

 

[Stat Assistant Professor]

Xiaofeng Shao's work is impressive but he is not a Bayesian. And his recent work doesn't seem to be focused at all on spatial statistics. Bo Li seems to do the type of research you're interested in though.

It seems like of the schools you listed, Purdue has the biggest group of professors who work on spatial statistics:  http://www.stat.purdue.edu/research/spatial_statistics.html

There are also a few very strong faculty who do work in Bayesian statistics at Purdue as well, including Faming Liang and Guang Cheng, although I am not sure how much spatial statistics research they do.

[Bayesian1701]

If you think you want to go Bayesian/spatial then go with a place where you have good advisor options in those fields. You might change your mind but you don't want to put yourself in a position where you are struggling to find an advisor to match your interests. I would cross Ohio State off the list.  At the end of the day, you can only choose one, and a good program overall may not be a good program for you.

[data_scrub]

On 3/13/2019 at 11:52 PM, Bayesian1701 said:

If you think you want to go Bayesian/spatial then go with a place where you have good advisor options in those fields. You might change your mind but you don't want to put yourself in a position where you are struggling to find an advisor to match your interests. I would cross Ohio State off the list.  At the end of the day, you can only choose one, and a good program overall may not be a good program for you.

Thanks for your advice Bayesian ? After visiting UIUC I think I'm pretty sure I won't be headed to OSU... I really enjoyed the visit and definitely like I'd fit better in Illinois. Now to visit the other two in the next few weeks!