Fall 2020 Masters/PhD Statistics Evaluation

[statapp123]

Hi, I just graduated college this past June, and I'm going to be applying to graduate statistics programs to begin in Fall 2020. Here is my profile.

Undergraduate Institution: University of Chicago

Majors: BS in Math, BA in Statistics

GPA: 3.87

Type of Student: Domestic Male

GRE General: 170 V (99%), 167 Q (90%), 4 W (57%) (I could also take and most likely do well on the Math GRE if it will help my app.)

Programs: MS/PhD in Statistics

Letters of Recommendation: This is a bit of a question mark for me. I will be asking professors who I've taken classes with. Two of these professors, I have developed relationships with by going to office hours. The third professor will not know me that well. Any advice on reaching out and developing a relationship with a professor (now that I've already graduated) is much appreciated!

Research Experience: Summer math REU after my freshman year, authored an expository paper related to probability.

Relevant Coursework: Real Analysis (three quarters, last of which covered measure theory), Linear Algebra, Probability, Statistical Theory and Methods, Abstract Algebra, Optimization, Numerical Analysis, Biostatistical Methods, Stochastic Processes, Algorithms, Complex Analysis, Regression Analysis

Programming: Took intro cs classes at my school and have proficiency in R from stat courses. 

Work Experience: TA for calculus, TA for high school math program, statistics tutor for undergrads.

My big question is whether I should be applying for masters or phd programs. I am interested in more mathematical statistics, and I think I would like to continue to a PhD eventually. But I think it might be a good idea to do a Masters first to see whether I like and am capable of research, as well as to get better letters of recommendation. I appreciate any advice people have!
 

 

Edited August 12, 2019 by statapp123

[Geococcyx]

Most of what I've heard on hear (I believe at least in part from bayessays, who might weigh in themselves) is that a master's won't really help that much barring special circumstances, e.g. changing fields and taking real analysis for the first time.  That is not an issue with you.  If you're wary about a PhD, then you are in luck -- UChicago has one of the two best statistics master's degrees in the country (along with Stanford), and unless all of your low grades were in real analysis or something, I don't have any reason why you wouldn't get in.  

 

Really, I think you can apply to most of the top PhD programs and work from there.  If you don't like or aren't capable of research, then you can choose to master/ABD out, without having to pay back loans from your master's tuition.  You'd have to do pretty well on the math GRE for Stanford to accept you, I think, but given that I didn't have a chance at places that highly-ranked, I don't think I can comment very accurately on your chances beyond just that you should do considerably better than I.  

[statapp123]

Do most Statistics PhD programs provide the option to Master out?

[Geococcyx]

I don't know about "most", and these days some schools will partially discourage it by requiring a master's thesis, but it seems fairly common.  I'm quite confident that NC State and Duke let people master out, and I know Stanford at least used to.  Plenty of others do, I'm sure, but as you might imagine I didn't research it at most places.

Edited August 13, 2019 by Geococcyx

[Stat Assistant Professor]

Second the advice above. With your GPA from University of Chicago and those math classes, you should be competitive for most top Statistics PhD programs. If you score well on the Subject GRE, you would have a definite shot at Stanford, but as it stands, I could see you getting into UC Berkeley, Columbia, etc. Having two strong LORs should help your application a lot too.

I would recommend only applying to PhD programs.

[bayessays]

Almost all programs allow you to master out. Since you think you might want a PhD, I would definitely apply to PhD programs - your profile is so good that a master's will not help you.  With your math background, high GPA at a school known for grade deflation, and amazing GRE score, I don't think you'll have to go outside the top 10 programs, with some safeties in the top 15.  If you can get a very high score on the math subject GRE, that will help for a few of the top schools - if you can get a 90%tile, it would be worth it, since you definitely have the profile for the schools that want it.

[statapp123]

Thank you all so much for the info--I think I will apply to PhD programs on your advice!

Two other questions: 

I'm curious about the importance of having undergraduate statistics research experience for applications. As I mentioned, I did a math REU for one summer during undergrad, but I don't have experience working with any professors, and I was wondering if that will hurt my application.

I was also wondering if anyone has any advice on leaning into relationships with professors and other potential recommenders. I have two profs from my undergrad classes who know me and whom I can probably ask for LOR's from, but I will need to ask for a letter from one professor who won't necessarily know/remember me too well. How can I re-introduce myself and explain my request? 

Thanks so much in advance! 
 

 

[Geococcyx]

Most people don't have undergrad stat research (particularly methods research, which is the most important kind for applications).  The math REU is a definite positive for you.  Your research background shouldn't be a problem.

Re: letters of recommendation, if the two professors you have close relationships with taught proofs-based math (esp. real analysis/measure theory) or statistical theory, or else were your advisor at your math REU, then you might be better-served by choosing a professor you do know well from a class that isn't strictly math or statistics.  I chose a professor from a genetics class because I thought it would tie-in well to how I was selling myself to departments.  If you want to talk about being a good statistics communicator, maybe get a professor from a communications/film/theater class that you know pretty well.  Maybe you like philosophy of science, and have a relationship with a professor from intro philosophy.  Maybe you like genetics or biomarkers or engineering statistics or forensic statistics -- choose accordingly.  

If those two professors aren't speaking to your ability in math/proofs, though, then my best advice would probably be to talk to them in-person, maybe talk about a class project/time you went to their office, and have your CV, transcript, and at least draft of personal statement/basic angle you're selling yourself through ready to talk to them about.  If you got a particularly high grade, that might also be something to note.