physics2stats

Undergrad Institution: Top 10 Private University Major(s): Physics Minor(s): Chemistry GPA: 3.88/4.00 Type of Student: Domestic white male GRE General Test: Q: 169 V: 169 W: 5.0 Grad Institution: Top 15 Public University Concentration: Computer Science MS GPA: 4.0/4.0 Programs Applying: Statistics PhD Research Experience: One paper published in undergrad on biological optics. Two other research projects -- one on reinforcement learning (paper on arxiv), one on uncertainty quantification (still in progress when I applied). Awards/Honors/Recognitions: A few merit scholarships; undergrad physics honor society; deans lists. Pertinent Activities or Jobs: I took five years off between undergrad and the above MS in CS. During that time I taught high school math and completed a master's in teaching (3 years) and then worked for an education tech company (2 years). Letters of Recommendation: One from a Biology professor, one from a researcher at Facebook AI Research (who was a physics postdoc when we worked together), and one from a Materials Science professor. I had done research with all of them. I think it was the first time any of them had written a rec letter for a statistics program. Math/Statistics Grades: Calculus Sequence (A's), Linear Algebra (A), Differential Equations (B), Analysis I (A), Complex Analysis (A), Numerical Analysis (A), Geometry (A), Probability (A), Stochastic Processes (A), Undergrad Math Stat (A), Linear Optimization (A), Nonlinear Optimization (A), Assorted CS courses (A's), Assorted Physics courses (A's, A-'s, and B+'s). Any Miscellaneous Points that Might Help: N/A Applying to Where: (All Stats PhD programs) Duke - Accepted NCSU - Rejected UNC - Rejected Harvard - Rejected Penn State - Accepted TAMU - Accepted Thoughts: I don't have any super coherent thoughts, other than I'm totally satisfied with where I wound up (Duke)! I had a preference to be in North Carolina, and thought I'd have the best shot at NCSU over UNC or Duke, so the NCSU rejection was definitely disconcerting. But Duke was my top choice and I couldn't be more excited to start in the fall! I just wish I could have been a fly on the wall when these committees were reading my application haha. Really, I felt pretty good about my odds at all these schools other than maybe Harvard, but I guess my changing fields multiple times plus the random work experience in education may have generated mixed reactions (e.g., interesting/well-rounded vs. chaotic/unfocused)? Or maybe that's reading way too much into things, who knows I guess I'd say at a philosophical level -- don't be afraid to aim high and put yourself out there, even if it's scary to change fields or go back to school. Two years ago, I had an ok job but knew I wanted more school at some point, so I figured what the hell and applied to some CS programs (despite my entire CS experience being one semester of intro to python). I got rejected by 7 out of 8 of them, but the one I got in was an awesome experience. This cycle, I felt way more confident, since I had waayyyy more relevant coursework under my belt plus some additional research and a more solid SOP, but I still had mixed results. So I guess just go for you want, roll with the rejections/acceptances (and expect both as a necessary part of life), and make the most of the opportunities you do get. And I'd say for grad apps specifically also cast a wide net, since there's a whole lot of randomness to the whole process. Good luck everyone!

Not sure how it works overall, but to give a bit of info for this year -- I got an offer on Friday and invited to a virtual visit on March 19. So just speculatively, your odds probably get worse the closer to that date it gets. Sorry you're stuck in limbo, but congrats on NCSU! (I applied there too but haven't heard anything yet.)

Anyone have any insight on the process at UNC Stats PhD? Do they typically admit in multiple batches?

It looks like in recent years there were at least a few acceptances spread out over different days. I also haven't heard, and I was feeling (cautiously) optimistic about my chances there, so I'm also stressed now haha.

Thanks for the quick response -- that's super helpful and comforting!

Hi All, I'm a pretty non-traditional applicant to Stats PhD programs -- I have a few questions, and am interested to see what y'all think of my chances! Student Type: Domestic White Male Undergrad: Top 10 overall (Private) (US News Rankings) Major: Physics (Chemistry minor) GPA: 3.88 Math Coursework: Calc 2-3 (A), Linear Algebra (A), Diff Eq (B), Complex Analysis (A), Numerical Analysis (A), Geometry Seminar (A) CS Coursework: Intro Programming (A-), Computer Architecture (A+ -- taken post-grad to prep for CS grad school) Other: Upper-level undergrad physics: Quantum I (A), Classical Mechanics (A-), Thermal Physics (A), Special/General Relativity (B+), Nonlinear Dynamics (A); Intro and Organic Chemistry Sequence (all A's) Graduate: Top 15 Computer Science MS (Public) (actually entering second year in the PhD program, but have decided I'm more interested in stats) Major: Computer Science GPA: 4.0 Coursework: Intro Artificial Intelligence (A), Intro to Theory of Computing (A), Intro to Algorithms (A), Probability Theory (A), Analysis I (A), Stochastic Processes (A), Linear Optimization (A), Machine Learning (Fall 2020), Nonlinear Optimization I (Fall 2020), Undergrad Math Stats (Fall 2020) GRE: Took in 2013, so it's expired and I'll have to retake. Scores then were V: 164, Q: 170, A: 5.0 GRE Math Subject: N/A Research: Publications: First author for a journal article on biological optics from undergrad supervised by a biology prof (cited 14 times as of posting this), Summer research on reinforcement learning under a physics postdoc (paper posted on Arxiv -- cited 2 times), worked on uncertainty quantification for ML methods in computational materials science since January 2020 -- hoping to get a paper by the time I submit applications this winter Misc: I'll be doing some data analysis for an education research group this fall -- (trying to apply ML methods to say something meaningful about user data for online education games) Letters of Recommendation: Planning to ask my three research supervisors (1 biology professor, 1 research scientist at Facebook now, 1 materials engineering professor). 2nd and 3rd should be strong. I think 1st should be strong too, but it's been a while since undergrad... I might ask my supervisor for my education research this fall if it goes well? Should I also ask a math professor? I don't think any of them would have a ton to say, other than "he did well in my class," which I'm thinking already comes across from my grades? Research Interests: Roughly: Developing applied/computational statistics methods for problems in the natural and social sciences Miscellaneous: I took 5 years between undergrad and my current grad program. In that time, I taught high school math and physics and got a MA in Teaching (3 years), and then worked for an education technology company designing online K-12 science/math curriculum (2 years). I really enjoyed both of those, but decided to go back to school because 1) I didn't see myself being satisfied in those career paths for an entire career, 2) I missed being in school and learning cool stuff all the time, and 3) especially after the reinforcement-learning research experience, I definitely bought into the "big data" hype, and wanted to be a part of it. I managed to sneak into a solid CS program, but once here I quickly gravitated toward the theory/math/stats side of things, and started considering mastering out and looking into stats. (As you can tell from my undergrad coursework, getting into top stats programs would have been tough without the probability/stats/analysis background that I've gotten in my current grad program.) Schools: Duke, UNC, NC State, Wisconsin, Michigan, Harvard, Texas A&M Questions: Thoughts on getting rec letters only from scientists in Bio, Physics, and Engineering? I'm aware my background is a pretty non-traditional -- I feel like it's given me a chance to grow personally and professionally, but any takes on how an admissions committee might view it? How much explanation do I need about transferring from CS PhD program to stats? Is just saying something like "I decided I want the rigorous theoretical foundation I would get through a Statistics PhD" sufficient? (Or, can I just frame it as an MS program I'll finish in May 2021 and leave it at that?) General thoughts on my chances at the schools I listed? Or suggestions for others? Thanks!