Stats/Biostats Profile Evaluation

[abstract_art]

Hey everyone, I'm applying to statistics/biostatistics PhD programs this fall. I posted one of these last year at the end of my sophomore year, but as the application season is coming up and my profile has changed a bit in the last year, I wanted to get a better feel for where I stand, given all of the information here is what's going to be on my application! I'm interested in machine learning and related areas.

 

Undergrad Institution: Top 35 undergrad, no statistics department, math department isn't that well known, cs department is completely unknown (no grad program)
Majors: Math, Computer Science
GPA: 3.94 (overall), 3.88 (Math), 4.0 (CS)

Type of Student: Domestic White Male

Courses/ Background:

Math Courses:

Honors Multivariable Calc (A), Honors Linear Algebra (A-), Differential Equations (A-), Probability (A), Mathematical Statistics (A), Analysis I (B+), Analysis II (A), Graduate Real Analysis (included measure theory) (A), Stochastic Processes (A)

I also took an independent study in a topic in knot theory/topology.

 

Computer Science Courses: All A's

Data Structures, Computer Systems, Computer Organization, Sophomore year theory courses, Object Oriented Design, Distributed Systems, Artificial Intelligence

I also took an independent study in machine learning.

I'm proficient in Python, R, and Java, and I know a few other languages at a decent level.

 

This fall I'm taking the first half of a year long Abstract Algebra course, undergraduate Complex Analysis, Algorithms in the CS Department, and I'm doing a thesis in ML in the CS department with the professor I did an independent study with.

GRE: Taking mid-August, will probably get 90+ percentile

Research Experience: Attended a SIBS program last summer, currently at an REU in a different biostats department than my SIBS program working on an ML project, will be working on my senior thesis while applying
Awards/Honors/Recognitions: Dean's List, Sophomore and Junior awards for being in top 5% of class, Pi Mu Epsilon (Math honors society)
Pertinent Activities or Jobs: Grader for the math department since the beginning of my sophomore year, TA for the CS department since the beginning of my sophomore year (last semester and this upcoming semester I TA'd for the professor I'm writing the thesis with)

Letters of Recommendation:

-CS professor I'm writing the thesis with (also took two classes previously with him in addition to the independent study/ TA'd for him last semester and this upcoming semester), should be very good

-Math professor I took the independent study in knot theory/topology with (also took Honors Linear Algebra, Graduate Real Analysis with him), should be pretty good

-Professor I'm working with at the REU this summer, should be as good as a rec letter can get after a summer of research

Thinking of applying to:

Stats: Chicago, Washington, Harvard, CMU (joint stat+ml), Duke, Penn, Wisconsin, Michigan, Columbia, Cornell, UCLA, Yale, Rice

Biostats: Washington, Harvard, UNC, Michigan, Minnesota

 

Some questions:

-Where do I stand with these schools as is? (Since my profile is pretty much fixed at this point)

-Does anyone know if for CMU's joint stat+ml program, if you're rejected from the joint program you're still considered for the stats program alone?

-I'm trying to decide whether to apply to Berkeley stats or biostats. Does anyone have any insight into how closely the biostats students interact with the stats department? There's a lot of faculty I'd like to work with in the stats department and I'm not sure if I'd be cut off from them in biostats.

-Is it worth it to apply to Stanford without taking the math gre? I've seen people say that it's possible for domestic students to get in without it.

Thanks!

Edited July 9, 2016 by marmle

[compscian]

@marmle I don't know about all the univs, but I can comment about the CS/EE and Statistics departments of UW, Penn, Columbia, and Rice. At UW, nearly all the admitted students with the ML emphasis in CSE, EE, and Stats departments had at least one published paper or in the pipeline. Similar was the case with Columbia. Penn and Rice are also great places -- I didn't visit these two, but was admitted. I was told that admission was competitive here as well, and professors looked for one really distinguishing factor. My understanding is that grades don't really matter much (my undergrad was in MechE with Applied Math minor) -- there would be 100s of applicants with really high grades anyway. Publications and research experience count a lot more. ML and related areas are insanely competitive at the moment, so I would recommend you apply to a few extra backup places.

PS: Operations Research in places like Princeton and GATech are also possibilities for ML/Stats related work, and are a little less competitive. Best wishes!

[MSc_in_SMC]

Your list of schools is reasonable for your profile.

When you apply to Carnegie Mellon joint statistics/machine learning, you can apply through the statistics department or the machine learning department. If you apply through the statistics department, you have the option of checking a box which allows you to be considered for both statistics and joint statistics/machine learning (I think it costs ~10 extra dollars application fee to check this box). I think you have a similar option of being considered for solely the machine learning department if you apply through the computer science application portal.

[abstract_art]

@MSc_in_SMC Awesome, thanks for the info!