Stat PhD: Purdue vs Ohio State for Spatial Statistics

[slowwalker]

Although I haven’t received all results, I think I will decide between Purdue and Ohio State. I am interested in spatial / spatio-temporal statistics and hope to go to academia in the future. Since PhD is a long training, I am also open to other research topics.

Here is some comparisons between the two programs, a lot of information is from "Trying to decide between Ohio State and Purdue" and "Stat PhD: UIUC vs Iowa State vs Purdue for Spatial/Bayesian". However, the former discussion was in 2015 and was mainly about computation finance, while the latter did not focus on Ohio State.

Purdue

- I am mainly interested in Prof. Hao Zhang and Prof. Tonglin Zhang's research in the department. While there is a spatial group list on Purdue's website, I think these two professor's research best fit to my interest.

- A little bit higher ranked (2018 US news: Purdue 27 vs OSU 37) and more prestigious, but the difference seems negligible?

- From current students, I heard that the department focuses a lot on the combination of CS or computation, but I am not very interested in this area.

- There are some negative past student perspectives about courses.

Ohio State

- I only found Professor Peter Craigmile doing research in spatial statistics, and I'm not sure whether this should be a concern. Ohio State was known for its spatial statistics group, but it seems that the group scale has reduced in recent years.

- 1 year Fellowship offer (no TA duties and pays slightly more)

- Since all students begin from master courses, the department has a structured course schedule. I had my undergrad in engineering and my master in Statistics, and I think such schedule may be helpful. However, OSU requires longer time to finish study and requires students to take two qualification exams.

 

There is no big difference for me to live in a small town or a big city, and both programs provide enough stipends for living. If anyone has thoughts on these schools or advice for me, I'd appreciate hearing it.

 

Edited March 24, 2021 by slowwalker

[Stat Assistant Professor]

Yes, Ohio State had a very strong spatial statistics group at one point including Noel Cressie and Tao Shi, who had great PhD placements (e.g. Jonathan Bradley at FSU was supervised by these guys). However, it seems as though the group has reduced in size. Both Cressie and Shi have left OSU. I would keep an open mind about research areas -- you may ultimately change your mind about what you're interested in, and nowadays, it is common for a lot of people who go into academia to change their research focus during/after their postdoc. This was probably less common many years ago (so you could spend your whole career studying the same topics), but nowadays, it's common to switch research focus.   

If you are considering academia, you may wish to consider academic placements of these departments, *in addition* to who the PhD advisors were for the graduates who went into academia. It seems as though OSU placed people in the past who worked on spatial statistics, but as you know, some of their more prominent spatial faculty have left. So it's good to look at historical data, in addition to whether or not those faculty are still at the school or not.

 

[bayessays]

In addition to the above changes mentioned by @Stat Assistant Professor, the biggest change in the OSU spatial statistics group recently is probably that Kate Calder left for UT-Austin.   You should definitely look at Sebastian Kurtek at OSU though - his research has a slightly different focus on shapes and images, but you might find it interesting as it is somewhat similar and some of his papers are essentially just spatial statistics.  From quick look, it also seems like Oksana Chkrebtii does some spatial statistics at OSU.

[slowwalker]

Thank you for your advice @Stat Assistant Professor and @bayessays. I have also received an offer from FSU. Indeed, Prof. Kurtek and Prof. Chkrebtii have some research about spatial and spatio-temporal statistics. (and Prof. Herbi as well) However, I am more leaning toward Purdue after looking at some of the programs’ academic placements. (I felt Purdue has better placements though it may be due to its larger department scale) Purdue also has more options in addition to spatial statistics. Those perspectives about the department's inclination and courses seems negligible after talking to another student graduated from Purdue.

Still, I would appreciate any additional thoughts or experiences with Purdue or OSU.

[AsianSpice]

not sure if you have made your decision yet, but Purdue is a better choice.

[CB20]

On 4/15/2021 at 6:14 PM, AsianSpice said:

not sure if you have made your decision yet, but Purdue is a better choice.

Could you expand on this? Are there no longer any big departments like Ohio that focus on spatial statistics? Seems like a lot of professors have dispersed in recent years.

[bayessays]

3 hours ago, CB20 said:

Could you expand on this? Are there no longer any big departments like Ohio that focus on spatial statistics? Seems like a lot of professors have dispersed in recent years.

I think Colorado State is the only strong program that has a large core of spatial statistics people (about half their faculty).