discreature

Hello all! I created a Discord server for applicants to Stats graduate programs a couple years back, but I'm only actually applying in this coming cycle. It's been dead for a while, so I thought it would be appropriate to revive it here. Send me a DM if you're interested in joining, as I would not like to post the link publicly in case of bots.

Hey all. I'm an undergraduate who's looking to apply to Ph.D programs in Stats in a couple years. I know this isn't necessary to know yet, but I'd like to have a good understanding of the subfields of Stats. It seems a bit opaque to me as of now. With a subject like math, when looking through professors' profiles there seems to be a list of about 10-12 broad research areas that people study (algebraic geometry, PDEs, number theory, etc.). Within stats, the research interests I see paint a less-clear picture. Also, level of detail tends to vary (a professor might list their research interests as "mathematical statistics"). In browsing through some profiles I've compiled the following list — what am I missing? Is there a resource you would recommend to become more familiar with the breakdown of subfields? Is there a reason for a less-clear hierarchy of stats research interests (when compared to math)? Applied Statistics Biostatistics Statistical genetics Statistics X Neuroscience Functional data analysis Statistics X Finance Statistics X Social Science Longitudinal analysis Causal Inference Theoretical Statistics High-dimensional statistics Non-parametric/semi-parametric statistics Statistical learning Bayesian statistics Signal processing Harmonic Analysis Probability Theory Stochastic processes This is the broad breakdown that I would make based on my current knowledge but I would like to know if this is missing anything major and/or if you think understanding the breakdown of the field is even helpful. Also, I'm sure there is nuance not included above (I assume there is a lot of applied Bayesian work and theoretical causal inference) but this is my broad understanding. Please correct me!

There've been a few threads recently that have touched on this, but I'm interested in asking directly: How much does Ph.D-level stats coursework differ school-to-school and what's your opinion on what should be taught to first/second year PhDs? There was a discussion recently in which someone stated they believe that most first-year sequences are outdated and do not teach the necessary topics for modern statistical research — do you agree? As I understand most schools will have a probability sequence (typically measure-theoretic) and some sort of theoretical statistics sequence (I hear Casella & Berger brought up a lot here). Are there other staples? Do you feel that these are all important to becoming a research-statistician? What's coursework that many are missing? In a practical sense, I'm going to have some space to take on courses that could potentially overlap with a Ph.D program and am looking to take things that will help me later on that might not be present in all curricula. One example of something that people have said would be good to take (although may not be in my curricula) is convex optimization.

Hello all. I've got some questions about the relevance of non-stats research. I'm currently first-authoring a paper in my university's medical school, but the focus of the paper is implementing a causal inference algorithm on a specific dataset. I am aware that this is not the type of research that I will do in grad school, but I feel that my work is statistically involved. Also, the professor that I have worked with on this project is the one who knows me the best thus far. Because of this, I intend to ask him to write me a letter of recommendation once application season rolls around. I of course hope to balance this out with strong math grades/recommendations from stats faculty, but I am wondering how big of a deal this research will be once I actually apply. Will this be seen as significantly positive experience or relatively ignorable by Stats department? Will an LoR from an Epidemiology Professor be looked down upon? I ask this not only for curiosity's sake, but also I am taking this coming year off of school and plan to make my research my main priority. Alternatively, I could continue research but shift my focus to perhaps self-studying some math/stats/GRE. I'm trying to suss out how I should divide my time between various things that are preparing me for Ph.D life/applications.

A lot of things I hear seem to suggest that math background is vital for Stats Ph.D admission, but this usually boils down into just Calculus, Linear Algebra, Real Analysis, and Probability. I was wondering what additional math courses would be helpful? I'm a math major who has completed these courses but still has over a year to go. There are some more advanced stochastic processes courses and some upper-div real analysis courses I'm interested in, but I wonder if this will have diminishing returns. In that case, would it be useful to take more stats methods courses? Or do admissions committees like any sort of math (e.g. Abstract Algebra, Number Theory)?

@bayessays Thank you for this response! It's hard to understand how admissions works as an undergrad, so the most simple way is to assume that there's a clean system of ranking and a simple deterministic way in which these things work. I think I do prefer that it is as you claim — a perfect system in which everyone has a "true ranking" and the universities simply sort based on that would be a bit demoralizing as well as more boring, so I'm glad it is not like that. I imagine the "true ranking" idea is akin to projecting a vector in 100-dimensional Euclidean space to a single real number — almost all meaningful information is lost. It's also reassuring to hear that not everyone at each top 10 program is a genius.

This is a question with probably no uniform answer and the truth is likely much more complicated than what I pose here. Regardless, I've been wondering about the structure of graduate admissions lately, particularly to T10 Ph.D programs in Statistics. Particularly, how top-heavy are applicant profiles? To elaborate, I imagine an "essentially perfect" profile has a student from a top undergraduate program with a 3.9+ GPA, 166+Q, 163+V, multiple research experiences, glowing LoRs from at least one famous faculty member, and completion of many high-level math courses. How many students like this are applying? I imagine there are about 120 or so spots in total at T10 universities. Are there more "essentially perfect" applicants than there are spots? If so, would the hairs be split upon the more "soft" traits? Like how much a certain reader knows an applicant's recommenders, or the impression that a reader gets from one's research experiences? My assumption would be that there are not that many "essentially perfect" applicants, as most universities include some statement about how incoming students without all desired background can make it up in the first year. This also makes me wonder about noise in admission. Implicitly assumed above is that (1) there is a true "ranking" of applicants and (2) faculty are able to discern this true ranking, and given a list of applicants they can sort it by this ranking and then admit the top 20 or so. So, I question these two assumptions. I believe in Biostatistics and many other fields, assumption (1) would be quite heavily violated. Many people in these fields apply directly to certain labs and are expected to know their research interests before entering. So, each subfield in these fields might have their ranking, but Student A specializing X might be incomparable to Student B specializing in Y. In these cases, the current department makeup and the makeup of the applicants could introduce noise to the admission. Perhaps Student A has a very strong profile, but specialization X only has one possible advisor at this university, so it is very easy for Student A to be rejected. I don't heavily believe this to be the case in statistics, at least based on discussions with Ph.D students and faculty it seems that a specialization is not by any means expected when applying, so this effect might arise less. One possible counterargument is that Student A might have very strong math skills while Student B has strong computing skills, but I'd intuit that departments prefer math skills. Overall, I'd imagine Stats applicants lightly violate (1), but generally follow it. The one that I am most unclear on is assumption (2). As it sort of rests on assumption (1), let us assume this. Consider $n$ applicants to University A who typically accepts $k$ students where $k<<n$. Now, let us enumerate the students and order them based on the "true rank" that exists (where a rank of 1 is the best and $n$ is the worst). So, a university that entirely satisfies (2) will admit the top $k$ students, and get an average ranking of $(k+1)/2$. Let's take the average "true rank" of a university to be our measure of assumption (2). So, the lower bound (AKA best case) would be an average true rank of $(k+1)/2)$ while the upper bound (a university that selects the $k$ worst applicants) would have an average true rank of $(2n-k+1)/2$. For $n=400$ and $k=40$ our best case is an average true rank of 20.5 and our worst case is an average true rank of 380.5. So, where in this interval do most universities lie? I imagine that you would never get a university that is close to the worst case, as there are initial screenings and also, it is clear that the top applicants would be visibly different from the bottom applicants, but how close do they get to the best case? As stated above I'm not exactly expecting an answer to this question, but would love to discuss this with others if anyone has insight on this or perhaps a strong case for or against assumptions (1) and (2), or point estimates on the number of "essentially perfect" applicants. I'd also like to add the disclaimer that this is definitely a gross oversimplification of the process, and moves a bit close to the "quantify people as just one number" mindset, which can be damaging. These are mostly just random quantitative musings that I found interest in and find myself personally involved in. As always the words of George Box are important — "All models are wrong, but some are useful."

Would statistics-relevant work or internships be relevant in graduate admissions? I'm thinking something like data science-related tech internships or quantitative finance positions that use statistics? Or would it be much better to try to focus up and study some Math/Stats? For context, this would be during a gap-year taken for COVID-related reasons.

Hello All. I'm going to be applying to Stats Ph.D programs in Fall 2021 (for hopeful admission to Fall 2022). Right now though, I'm planning my classes out for Junior Year and I've got a few hang-ups. Basically, Between the following set of classes I can choose one (all likely taught fall): Measure-Theoretic Probability Theory (First required probability class for Ph.Ds) Likely the one that would "look best" when applying, but also the most time consuming. Furthermore, I don't think it's super expected that I take this since it's Ph.D Level? I guess there's some worry that I should be focusing on the fundamentals before going this deep. Abstract Algebra (Group and Ring Theory) Probably the one that's least relevant to Stats, but I haven't taken Algebra before and I plan to take the Math GRE (intend to apply to Stanford) and feel that this could do good for my score. Also, at the very least this might convey mathematical maturity? Linear Dynamical Systems (Would be my first applied Linear Algebra course, and the required prereq for our optimization course) Probably the one I'm most interested to take at this stage. Covers some signal processing stuff, and I think it would be good to have a strong performance in Linear Algebra that is recent (my previous Linear Algebra course will have been almost 2 years old when I apply) And also can choose one between the following set of classes (all likely taught winter): Functional Analysis Seemingly helpful for Stats? Not super direct, but I think also probably flexes Lin Alg and mathematical maturity. Number Theory Same argument as Abstract Algebra. Also, notably, I'll likely take the courses not taken this year next year (so the fall courses might appear on some applications depending on due dates). Let me know if you have any thoughts on these choices or any other questions! Thank you in advance.

Thank you for the info! Sorry, I prematurely posted and then added in my info, if you're willing to take another look.

Hello! I'm planning to apply for Stats Ph.D programs in Fall 2021, so I'm currently a rising Junior. I don't have a lot of my profile finalized since I've still got a one more year, but I guess if this could be sort of an evaluation plus a recommendation for what holes I should focus on filling this coming year, that would be amazing! Edit: I realize that I'm unsure about the terminology? I plan to apply in Fall 2021 to programs that start in Fall 2022. Sorry if that's confusing and please correct me if I was wrong. Undergrad Institution: Top 3 Stats University (US News) Major: Mathematics GPA: 3.71 Type of student: Domestic male (URM) GRE (I haven't taken it yet) Relevant courses: Math: Calc III (B+), Linear Programming (A), Intro to Probability (B+), Combinatorics (Pass), Real Analysis I (A), Proof-Based Linear Algebra (A), Real Analysis II (Pass, Covid Quarter), Differential Equations (Pass, Covid Quarter) ** I plan to additionally take a course on Measure Theory, Measure-Theoretic Stochastic Processes, Linear Dynamical Systems, and Functional Analysis next year. Stats: Data Analysis (A), Intro to Regression (A-), Longitudinal Data Analysis + Survival Analysis (Pass, Covid Quarter) ** I plan to additionally take Mathematical Statistics and a second Regression/ANOVA class next year CS: Intro to Programming (A), Programming II (B) ** I plan to additonally take Analysis of Algorithms and Machine Learning Research: 8 or so months working on a Public Health research project where I am implementing some Statistical Models. Hopefully will turn into paper. Other: I've taken part in a Measure Theory directed reading program that resulted in a small talk. Programs Considering: Not sure where I fit yet, but hopefully want to apply to the highest ranked universities that I have a chance at. Right now I think the gaps in my application are probably my Bs in various classes, but I hope that since they were all Freshman year that it will be weighed accordingly. I think my grades this coming year in the planned courses should be pretty solid as I've focused up and hit my stride, I believe. Please let me know any comments you have or suggestions for things I could do/classes I could take in the following year! Also, aside from the fact that LORs usually come from more well-known people, does the university you went to actually have a significant impact? Also, does being Domestic and URM actually help much? Department websites obviously don't divulge this info.

Not the most inventive advice but I've definitely had more responsiveness when a prof that I know introduces me to them. Over email this is as easy as them just sending them an email with a brief intro and CCing you. So maybe you know someone form your uni that knows at least some of them? Best of luck

Hello all! Hopefully this is allowed. I made a discord server for those applying to Stats Ph.D programs. I don't know others doing so at my school and thought a place to chat about these things would be nice. There's a channel with resources and I'd like to share my own discussions with faculty as well. I imagine it's use as opposed to GradCafe could be to ping others if you have a question that doesn't necessitate a full thread or just generally getting to know others. If you're interested, DM me! I don't want the link public just in the case of bots etc. (Sorry if this is breaking the rules)

Hi all. Currently I'm a second-year undergrad who is interested in applying for Stats Ph.D programs my senior year. Overall, I'm relatively on track in terms of taking courses, getting involved in research, and such. I have one potential glaring hole though, my first year the transition to college was a bit tough, and I got some Bs in relevant courses. Namely Calc II and Probability. Almost all Stats programs emphasize these two courses as being important. Retaking these courses would be possible but I don't think it's worth it since it's just a B, but how can I show future grad schools that I'm not actually weak in those areas? I currently plan to take mathematical statistics (which has probability as a strong prereq) and perform well there, as well as take stochastic processes and perform well, but what courses could I take/things could I do to make up for my Calc II grade? Is high performance on the GRE (or Math Subject GRE) and higher level math courses enough, or is there something else? Or perhaps I'm overthinking this.