2021 Fall Stat Prof Eval

[JS99]

Heyo yall, I'm currently applying to some PhD programs in stats and I'm trying to gauge how competitive I will be.

Undergraduate Institution: R1 state school, top 100ish US News, not particularly well-known
Major: Mathematics and Economics
Minor: Data Science
GPA: 4.00
Type of Student: Domestic white male (I am not straight tho I have absolutely no idea if I should include this on my app)

Research Interest: Econometrics, applied statistics in social sciences, ML
GRE Score: 168Q/160V/4.5, no math subject test cause it was canceled

Math classes: Calc III (A), Basic Concepts in Math, an intro to proofs class (A), Real Analysis I and II (A), Linear Algebra (A)
Stat classes: Probability theory I (A), Probability Theory II (A), Mathematical Statistics (A), Data Analysis and Stats Computing (A), Intro to Machine Learning (in progress)
Misc classes: Mathematical Economics, basically a lot of linear algebra and its applications (A), Econometrics I and II, at the graduate level (A), Python Programming (A), more programming and data science courses (in progress)

Research Experience:

Year-long research grant in econometrics, leading to a paper (not published) but presented at a conference

Currently a research assistant, using Python to do natural language processing in the social sciences, currently drafting a paper on Machine Learning techniques that coincide with this project

Work Experience:
Just some work as a data manager Sophomore year to pay some bills

Awards:
Dean's list all semesters

2nd prize for Econ paper in my department

Letters: 
Currently deciding on three of the following, in order by how strong I think they'd be:

Sociology professor who I am working with right now, publishes applied sociology papers

Econ professor who I worked with on my econometrics paper, publishes applied econ papers

Math professor in all of my proofs class including real analysis where I was one of the best students, does not publish anymore

Math professor in prob theory II where I succeeded after going to office hours a lot, publishes stats papers

Schools:

University of North Carolina, University of Chicago, University of Washington, UPenn, Wisconsin-Madison, UCLA, University of Toronto, University of Michigan, Colombia, Carnegie Mellon, Penn State, Iowa State

Any other school suggestions/letter suggestions or any other suggestions would be greatly appreciated! Thanks yall

[StatsG0d]

Your profile is strong, but based on your research interests I think you'd be better off being placed in economics departments or some of those quantitative methods in social sciences (QMSS) PhD programs (e.g., at Columbia or Michigan).

There are some people in biostats and stats doing causal inference research, which is related to economics, but overall I would say econometrics folks have the edge. Econometrics and statistics, while related, can really be quite different.

[JS99]

On 9/21/2020 at 7:27 AM, StatsG0d said:

Your profile is strong, but based on your research interests I think you'd be better off being placed in economics departments or some of those quantitative methods in social sciences (QMSS) PhD programs (e.g., at Columbia or Michigan).

There are some people in biostats and stats doing causal inference research, which is related to economics, but overall I would say econometrics folks have the edge. Econometrics and statistics, while related, can really be quite different.

Thanks for the feedback! I guess I didn't really make myself as clear as I should. I am mostly interested in high-dimensional inference and machine learning techniques as they apply to the social sciences. Right now I am working on a project that employs the word2vec technique on several financial documents. I am learning about neural networks and this is a great interest of mine; many of the economics programs unfortunately do not interest me very much. I'll check out some of the QMSS PhD programs, but I am particularly interested in statistics programs as they appear much more empirical.

[StatsG0d]

13 hours ago, JS99 said:

I am particularly interested in statistics programs as they appear much more empirical.

I disagree with that. The training in the vast majority of stats programs is very theoretical, especially at the schools you've mentioned. You can do something applied for your dissertation, but it will likely need at least a bit of new methods / theory.