2014 USNWR Rankings (Statistics/Biostatistics)

[ParanoidAndroid]

With the updated rankings slated to be published tomorrow, I thought this would be a good topic to discuss them. Here is the article regarding upcoming new rankings:

 

EDIT: New rankings posted! 

 

http://grad-schools.usnews.rankingsandreviews.com/best-graduate-schools/top-science-schools/statistics-rankings

 

 

Here are the old rankings:

 

2010 Statistics rankings (Top 40):

 

1) Stanford

2) UC Berkeley

3) Harvard

4) Chicago

5) Washington

6) Carnegie Mellon

7) Duke

8) North Carolina State University

9) Texas A&M

10) Pennsylvania

11) Wisconsin-Madison

12) Michigan-Ann Arbor

13) Minnesota

14) Iowa State

15) Penn State

16) Coumbia

17) Cornell

18) Purdue

19) UNC-Chapel Hill

20) Ohio State

21) UCLA

22) Florida

23) UC-Davis

24) Illinois-Urbana Champaign

25) Iowa

26) Yale 

27) Rutgers

28) Rice

29) Colorado State

30) Florida State

31) Connecticut

32) Michigan State

33) Boston U

34) Pittsburgh

35) George Washington

36) Northwestern

37) Georgia

38) Missouri-Columbia

39) Virginia Tech

40) Southern Methodist

 

NOTE: I realized that some of these programs were equal in rating, so some of these schools are in fact tied. 

 

2010 Biostatistics Rankings (Top 20)

 

1) Harvard

1) Washington

3) Johns Hopkins

4) UNC-Chapel Hill

5) Michigan-Ann Arbor

6) UC Berkeley

7) Minnesota

8) Wisconsin-Madison

9) UCLA

10) Columbia

11) Emory

12) Iowa

13) Boston U

13) Pittsburgh

15) U Texas Health Sciences Center

16) Medical College of Wisconsin

17) Medical U of South Carolina

18) Buffalo-SUNY

19) Virginia Commonwealth

Edited March 11, 2014 by ParanoidAndroid

[ParanoidAndroid]

Let me know if I made a mistake there. 

[Stat Assistant Professor]

Looks like the updated rankings were just posted. http://grad-schools.usnews.rankingsandreviews.com/best-graduate-schools/top-science-schools/statistics-rankings

[ParanoidAndroid]

Looks like the updated rankings were just posted. http://grad-schools.usnews.rankingsandreviews.com/best-graduate-schools/top-science-schools/statistics-rankings

 

Wow, that must have been minutes after I posted this thread. 

[Stat Assistant Professor]

Heh. I am creating separate lists for statistics and biostatistics right now, will update this thread when I am done. Also, there are ties on the USNWR list so just because a school is listed below another does not mean that the one below it is ranked lower (U.S. News considers them equally ranked).

[Nightgaunts]

Why are some schools listed twice? UW, Harvard, and University of Michigan-Ann Arbor all seem to be listed twice.

[ParanoidAndroid]

Thanks Applied Math to Stat! 

 

Why are some schools listed twice? UW, Harvard, and University of Michigan-Ann Arbor all seem to be listed twice.

 

They don't separate the biostats and stats rankings. 

[Stat Assistant Professor]

Biostats and stats are both ranked on this list. You have to click on the individual school to see stats vs. biostats. I am segregating the two right now, will post to thread when I'm finished

[ParanoidAndroid]

Glancing at the new rankings, looks like the only new addition in the top 40 is NYU Sterns program (for statistics only). 

[faerare]

Hm... are you sure the updated rankings have been posted already? On the main page (http://grad-schools.usnews.rankingsandreviews.com/best-graduate-schools), there are links to previews of the 2015 list.

 

Edit: Clarified my question!

Edited March 11, 2014 by faerare

[ParanoidAndroid]

Hm... are you sure these are the updated rankings? On the main page (http://grad-schools.usnews.rankingsandreviews.com/best-graduate-schools), there are links to previews of the 2015 list.

 

The rankings I listed in the OP are the 2010 rankings. Thought I would post them to compare. Seems like there isn't much of a difference in the Stats' programs. But there have been several new Biostat programs added in the 2014 edition. 

[Stat Assistant Professor]

To separate statistics from biostatistics (these are the 2015 rankings):

 

STATISTICS

1. Stanford

2. UC Berkeley

3. UChicago

4-5. Harvard, Washington (tied)

6. Carnegie Mellon

7. Duke

8. UPenn

9. Wisconsin

10-12. NCSU, Texas A&M, Michigan (tied)

13. Iowa State

14-17. Minnesota, Columbia, Penn State, UNC Chapel Hill (tied)

18-19. Cornell, Purdue (tied)

20-21. Ohio State, UC Davis (tied)

22-23. UCLA, Florida (tied)

24-26. UIUC, Yale, Iowa (tied)

27-29. Florida State, Rice, Rutgers (tied)

30-31. Colorado State, UConn (tied)

32. Michigan State

33-35. NYU, Northwestern, Pittsburgh (tied)

36-39. George Washington, Georgia, Missouri, Virginia Tech (tied)

40. SMU

41-45. UCSB, Arizona State, Oregon State, South Carolina, UVA (tied)

46-47. Temple, UC Riverside (tied)

48-49. Kansas State, Colorado-Denver (tied)

50-52. Baylor, Case Western, Kentucky (tied)

 

BIOSTATISTICS

1-2. Harvard, Washington (tied)

3. Johns Hopkins

4-5. Michigan, UNC-Chapel Hill (tied)

6. UC Berkeley

7. Minnesota

8. UPenn

9-10. Columbia, UCLA (tied)

11. Yale

12. Emory

13. Brown

14-15. Iowa, Rochester (tied)

16. Pittsburgh

17. Boston University

18-20. Medical College of Wisconsin, UIllinois-Chicago, UTexas-Houston (tied)

21. Case Western

22. Medical College of South Carolina

23-25. SUNY Albany, Alabama, SUNY Buffalo (tied)

26. South Carolina, Virginia Commonwealth

Edited March 11, 2014 by Applied Math to Stat

[StatPhD2014]

Michigan is tied with ncsu and Texas A&M

[Stat Assistant Professor]

Michigan is tied with ncsu and Texas A&M

thanks, I edited my post. I might have made some other errors in there but the general rankings are correct (I think...)

[Stat Assistant Professor]

i randomly checked the websites of some of the schools ranked from Colorado State & UConn and higher, and it seems as though job placement is pretty solid at all these schools... though of course, the faculty at the top tier schools nearly all have their PhDs from other top tier.

[wine in coffee cups]

According to the methodology, they have averaged survey results from fall 2009 and fall 2013 to compute these scores, so these don't completely reflect current perceptions vs. the 2010 version. Eyeballing the 2014 vs. 2010 reputation scores, it looks like most top programs remained the same or were nudged up one decimal place, with the biggest movement I see being Wharton bumped from 3.9 to 4.1. That reflects what I think a few people here have suggested, that Wharton has had some gains in reputation as of late and would be ranked even higher if just using the more recent data.

 

Also:

Response rates for the doctoral Ph.D. sciences were as follows: for biological sciences, 9 percent; chemistry, 18 percent; computer science, 35 percent; earth sciences, 17 percent; mathematics, 24 percent; physics, 29 percent; and statistics, 39 percent.

 

  statisticians

[stats_applicant]

Stanford 4.9 4.9

Berkeley 4.7 4.7

Chicago 4.3 4.4

Harvard 4.3 4.3

Washington 4.3 4.3

CMU 4.1 4.2

Duke 4.0 4.1

Wharton 3.9 4.1

Wisconsin 3.9 4.0

NCSU 3.9 3.9

Texas A&M 3.9 3.9

Michigan 3.8 3.9

 

So assuming they did a 50-50 average of 2009 and 2013 (which admittedly is a wild assumption) the 2013 survey alone of the top few would look something like

 

1. Stanford 4.9

2. Berkeley 4.7

3. Chicago 4.5

4. Harvard 4.3

4. Washington 4.3

4. CMU 4.3

4. Wharton 4.3

8. Duke 4.2

9. Wisconsin 4.1

10. Michigan 4.0

11. NCSU 3.9

11. Texas A&M 3.9

 

putting Wharton in the top five.

[literaryreference]

Also no mention of BU's stat program, only biostat. Is this meant to be comprehensive in any way? Does a school need to actively court USNWR to attain a ranking? If this is the best they can do, I'm going to substantially deemphasize these rankings in my decision, I don't think these accurately reflect the consensus opinions of the academic community outside of the very top tier. Any chance Cyberwulf, or any other academics could weigh in on this?

[wine in coffee cups]

Many of the schools I applied to are not mentioned anywhere on this list including George Mason, University of Arizona (which has to be better than Arizona State), U Maryland College Park (which has a very good reputation), U Maryland Baltimore County, U Mass, SUNY Stonybrook (very good school), and a few others. My impression is that this list is a regurgitation of the obvious top 10, and blows at discriminating outside of that range.

 

Also no mention of BU's stat program, only biostat. Is this meant to be comprehensive in any way? Does a school need to actively court USNWR to attain a ranking? If this is the best they can do, I'm going to substantially deemphasize these rankings in my decision, I don't think these accurately reflect the consensus opinions of the academic community outside of the very top tier. Any chance Cyberwulf, or any other academics could weigh in on this?

 

All of the programs you named (besides George Mason) are not standalone statistics programs, but rather concentrations in statistics housed inside math, applied math, or "mathematics and statistics" departments and thus ranked under math.

[CauchyProcess]

All of the programs you named (besides George Mason) are not standalone statistics programs, but rather concentrations in statistics housed inside math, applied math, or "mathematics and statistics" departments and thus ranked under math.

 

In this case, how do we determine what the ranking applies to? How to distinguish whether a department of this type has a strong reputation in stuff like geometry/topology vs statistics/probability?

[stats_applicant]

In this case, how do we determine what the ranking applies to? How to distinguish whether a department of this type has a strong reputation in stuff like geometry/topology vs statistics/probability?

 

The US News rankings do include some subfields:

http://grad-schools.usnews.rankingsandreviews.com/best-graduate-schools/top-science-schools/mathematics-rankings

 

Unfortunately, it doesn't include probability/statistics.

[wine in coffee cups]

In this case, how do we determine what the ranking applies to? How to distinguish whether a department of this type has a strong reputation in stuff like geometry/topology vs statistics/probability?

If you're trying to assess reputation, you look at the main signalers that the faculty US News surveyed would have likely had in mind. I think things like: how many people in the department are well-known figures in the statistics community (highly cited publications, awards, frequently invited to give lectures at conferences or other departments)? Are faculty generally publishing in reputable statistics journals and the big machine learning conferences (as opposed to unknown journals or almost entirely niche venues for their area of application)? Do a fair number of PhD graduates place into nice-sounding academic positions?

[ParanoidAndroid]

Also no mention of BU's stat program, only biostat. Is this meant to be comprehensive in any way? 

 

It's strange considering BU Stats was a top 25 program in the previous rankings. 

[cyberwulf]

Also no mention of BU's stat program, only biostat. Is this meant to be comprehensive in any way? Does a school need to actively court USNWR to attain a ranking? If this is the best they can do, I'm going to substantially deemphasize these rankings in my decision, I don't think these accurately reflect the consensus opinions of the academic community outside of the very top tier. Any chance Cyberwulf, or any other academics could weigh in on this?

 

Honestly, the rankings look fairly reasonable to me, though you could make the case for some programs to move up/down by a couple of ranks. Most of what these rankings measure is reputation, and since perceptions are slow to change they tend not to pick up on "recent" developments (i.e., things that have happened in the past 10-20 years). For example, I think that Iowa State might be a tad over-ranked relative to their current strength, likely because they were a legitimately elite program 25+ years ago.

[clurp]

Stanford 4.9 4.9

Berkeley 4.7 4.7

Chicago 4.3 4.4

Harvard 4.3 4.3

Washington 4.3 4.3

CMU 4.1 4.2

Duke 4.0 4.1

Wharton 3.9 4.1

Wisconsin 3.9 4.0

NCSU 3.9 3.9

Texas A&M 3.9 3.9

Michigan 3.8 3.9

 

So assuming they did a 50-50 average of 2009 and 2013 (which admittedly is a wild assumption) the 2013 survey alone of the top few would look something like

 

1. Stanford 4.9

2. Berkeley 4.7

3. Chicago 4.5

4. Harvard 4.3

4. Washington 4.3

4. CMU 4.3

4. Wharton 4.3

8. Duke 4.2

9. Wisconsin 4.1

10. Michigan 4.0

11. NCSU 3.9

11. Texas A&M 3.9

 

putting Wharton in the top five.

 

You've got an unconventional approach to taking averages, for sure. 

 

Wharton's average ends up being higher than the scores it received in either year. Same for some of the other schools ...