Geococcyx

So far as I know, such statistics aren't collated in one central location, so you'll have to check each school. If they aren't posted on a school's website, then you can ask the director of graduate studies (or the director of the master's program, if they have one) and they can often provide some info to that effect.

There have been a few people on the forums who did master's at NC State, but I don't know that any of us would have background on the environmental concentration. Obviously the folks at NC State would be your best contacts if you wanted to ask them about the basic details (they appear to not have a specific master's program director listed, so I guess the DGS, Wenbin Lu, would be the choice there?). She's probably quite busy, but Elizabeth Mannshardt might be somebody to ask if you're really interested in the program at NC State; she's an adjunct at NC State and is an administrator in the local EPA branch (and hence, probably works with some of the interning environmental stats students). Normally I wouldn't just pull someone's name out of thin air like this, but she was recently president of North Carolina's ASA chapter and has worked on early-career mentoring of statisticians, so she might be more receptive to outreach than the average person. I don't know much about other stat departments, but I think Ohio State's statistics department is also pretty environmentally-oriented. They've lost a few professors in that area (Kate Calder & Noel Cressie come to mind), so maybe less so now than in the past, but it might still be worth some interest.

Just for clarity, the research would be more important if you wanted to continue on to a PhD in Biostatistics or a similar field. If you wanted a PhD, then I'd think twice about dropping your research, since even research experience in non-statistics fields can be helpful to PhD applications. For a terminal master's, though, you shouldn't worry about weakening a selling point of yours by quitting the research; I don't think most master's care very much about your research background, and even if they did, your GPA plus good performance in math classes and on the GRE should be more than enough.

I'm not the expert, so look for future posts for more veteran forum members, but I can at least give a first pass. In a vacuum, yes, the other upper-division math courses are helpful. Getting high grades in proofs-based classes will be helpful to your profile. However, I also think the graduate math stat sequence would be helpful, particularly if it's taught out of Casella and Berger (or so my impression would be, from this forum). As for the other stat courses, if they're at the grad level then they might be helpful, but if they are undergrad then I don't know that they'd do much for you. If you are just trying to give yourself the strongest possible admissions profile for a Stat PhD, then I'd personally recommend taking the graduate math stat sequence plus an upper-division math course or two (there are some applications of algebra and geometry in statistics, for instance). This is with me not being sure what level the other stat classes are at, but I think this is probably the most reasonable option overall. If you have low grades in past proofs-based classes, then the importance of other upper-division math courses requiring proofs would probably increase.

Plenty of people don't have super specific research ideas when going into a PhD. I had a few application areas of interest and a general desire to work on model selection that wasn't particularly fleshed-out, and got into plenty of PhD programs without even having done any methodological stat research. If you were going to go into epidemiology, for instance, you'd want a topic pretty well in-hand for PhD work, but you'd be fine in statistics or biostatistics going straight to a PhD without a clear topic in mind. Not that that is inherently the best option for you, of course, but a lack of granular research topics shouldn't be a reason to write off applying directly to stat or biostat PhD programs.

I agree with Bayessays. I think I should add that one mistake people sometimes make in choosing PhD programs is choosing a bunch of prestigious private schools on name reputation, without giving proper attention to public programs that are often larger (meaning, relatively easier to get into) and potentially better. I know I made that mistake on a first pass, and was fortunate to learn otherwise here on gradcafe. Getting a PhD at NC State or Illinois (etc.) might not sound as prestigious to an uniformed stranger, but academics or smart industry people will know that those are strong programs. Just in case you haven't looked at it yet, the USNews grad school rankings in statistics are a good place to start, and since those are kinda confusing in format, feel free to contact me with questions via DM. They aren't everything, though, so don't stop there!

Disclaimer: I'm still in undergrad, this is just what I've seen on the forums. They shouldn't care that much about a lack of bio experience. Frankly, I thought I had at least an OK bio background, and it didn't seem to do me much good. Focus on your math background, you'll be OK! I think genetics is the one area you'd want some bio background, but you can just do other applications of CI instead.

You don't appear to have mentioned what your grades were in Real Analysis -- do you mind mentioning them, along with grades in any other proofwriting-based classes? Assuming that your grades in Real Analysis were uniformly B or above, it's definitely realistic to apply to PhD's next year (certainly so if you got all A's or 2 A's and a B+ or something). That's particularly the case if you mean a public school in the US News top-50 (as I'm assuming), rather than one of the top 50 public schools listed on US News, and also (as I'm assuming) that you're a domestic student. Go check my profile over in this thread: https://forum.thegradcafe.com/topic/117853-2019-applicant-profiles-and-admission-results-for-statisticsbiostatistics/. There are some school prestige and research experience differences that would probably balance each other, particularly with the benefit of actually working in the field for a little bit. I know with my profile I was advised against applying to master's because they'd largely be a waste of my time/money, so I imagine that might hold for you too.

I'm not sure about the later chapters, but the first 6 or 7 chapters appear similar in content to Devore and Berk's Modern Mathematical Statistics with Applications. I'm not quite clear about what sort of difference in content depth there is between the two, but Devore and Berk is pretty friendly in my experience.

Hey, just wanted to let folks on the waitlists know that I declined my other two offers (out of the three top North Carolina schools), so if you're still waiting on any of them make sure to keep an eye out.

I understand that people probably don't have strong opinions on the topic, but figured I might as well check: who do people think is the best machine learning researcher at Duke/UNC/NC State? They all have some excellent folks who list machine learning as a research area (e.g. Dunson/Mukherjee, Kosorok, and Laber), but plenty of them do a lot of research outside of machine learning too, and it's hard for me to separate out all of their research areas and decide how strong each subject is. As something of an aside, or perhaps a path to alternate answers if people just don't have any opinions on the machine learning research at these schools that they're willing to share (publicly or via DM) -- I usually look for publications in the Journal of Machine Learning Research and IEEE Transactions as a sign of good machine learning research, but are there other journals I should be considering too? Regardless, have a great weekend everyone!

I recall that cyberwulf has usually said it's about the tenth best biostat program (I think that's roughly Columbia/MD Anderson/UCLA territory in US News for whatever that's worth). They have an alum who is the stat/analytics director for the NFL right now, so I wouldn't worry about industry too much. They've had some decent academic placements I think-- I thought they had someone become a professor at Minnesota biostat, although I might be misremembering which department at Minnesota they are in. Given the size of the program, there's not really a big pool of students to be achieving gaudy placements or titles with, so I wouldn't be too worried myself if their top placements aren't quite as amazing as somewhere else that's bigger and has more bites at the apple.

@Aweaston You probably already saw it, but just in case, there was some discussion of adviser choice at UNC biostat in this thread: EDIT: Oh yeah, statistical genetics is a promising field, and UNC is good at it. I think that is Danyu Lin's primary research area, and he's a Spiegelman winner if I recall correctly.

Disclaimer: I don't know anything more than you, let alone the other responders. I'd choose UNC biostat myself, but a lot of my research interests are in biological applications anyways. What are your reasons for wanting to study statistics instead of biostatistics? That would help inform our advice. I suspect you could go to industry or academia from either place. If you were looking at biostat faculty jobs the UNC would probably be better, but I don't know how it would play out for stat faculty jobs. If you wanted to work in the FDA, then UNC would be a better choice too. You mentioned a couple prestigious faculty at UC Davis last time you posted who you seemed interested in -- do you have particular faculty you are interested in at UNC?

Thank you! Just to confirm, were any of these opportunities involving collaboration just within the statistics department, or did they all involve outside profs/departments? It sounds like the latter.

I get the sense that part of the experience of being in a biostatistics department is the opportunity for lots of collaborative research -- collaborating with various biomedical research groups at your university, groups in other parts of a school of public health, and collaborating with other professors in your department on both those projects and on projects native to the biostatistics department. Given the nature of large medical grants from the NIH/NHLBI, I understand that such collaborating is pretty much necessary, although it may be a cultural preference in those departments too. I am curious, then, at the extent of collaborative research that occurs in the standard statistics department. Do statistics PhD students work much with professors who aren't their PhD advisers, excepting in statistical consulting centres/cores? If students are working with non-adviser professors outside of specific consulting relationships, are those professors more likely to be in other departments (e.g. biology, hydrology, atmospheric sciences), or do PhD students also work on projects/publish papers with statistics professors who aren't their adviser? I understand this is liable to vary a lot department-to-department, and given that I think most of the current and former graduate students who frequent this forum are/were in biostatistics departments, I'm dubious that I'll hear any anecdotes one way or another about this. Even so, let me know if you do have any knowledge one way or another about this, and have a great weekend everyone!

Undergrad Institution: Big State School, US News top 80 or so overall Major(s): Statistics, Physics, Psychology (applied as a Math major too, decided not to take a non-statistics-related math class) Minor(s): Math GPA: 3.80 Type of Student: Domestic white male, very bland diversity-wise GRE General Test: Q: 170 (96%) V: 167 (98%) W: 5.0 (98%) Programs Applying: Statistics/Biostatistics PhD programs Research Experience: Mostly some social science/psychology research, a little bit of stuff with epi/biostat this year. Awards/Honors/Recognitions: Phi Beta Kappa Pertinent Activities or Jobs: Some public speaking/science communication stuff Letters of Recommendation: Psychology research mentor (department head, did senior thesis with them), genetics professor from a class taught entirely off of journal article discussions, and a professor I had for 1 applied statistics class. Math/Statistics Grades: Calc I (AP Credit), Calc II (B+), Calc III (A-), Diff Eq (A), Linear Algebra (A), Proofs & Logic (A), Intro to Sequences [there were proofs in this, to be clear] (A-), Probability (A), Stat Inference (A*), Real Analysis (B*), a bunch of other applied stat classes that I got all A's in. * indicates that I was taking that class during the applications, hence only schools with late application deadlines (UNC biostat and Columbia stat) or that specifically requested transcripts (Wisconsin stat) got those grades. Any Miscellaneous Points that Might Help: Did SIBS at NC State, profs at my university might have had a few connections they used on my behalf but I don't really know. Any Miscellaneous Points that Might Hurt: Zero grad classes, lots of withdrawals, pretty lacking proofs background, strange choice of letter-writers (no professors from proofs-based classes), really weird personal statement. Applying to Where: Carnegie Mellon - Stat PhD / Rejected (2/18) Duke - Stat PhD / Admitted (2/7) / I might go here, not saying Columbia - Stat PhD / Rejected (3/14) NC State - Stat PhD / Waitlisted (1/30) / Admitted (4/2) / I might go here, not saying Wisconsin - Stat PhD / Admitted (2/22) / Declined UCLA - Stat PhD / Admitted (2/09) / Declined Illinois (UIUC) - Stat PhD / Admitted (1/08) / Declined Ohio State - Stat PhD / Admitted (2/1) / Declined Harvard - Biostat PhD / Rejected (2/15) Johns Hopkins - Biostat PhD / Rejected (2/26) UNC - Biostat PhD / Admitted (1/22) / I might go here, not saying Minnesota - Biostat PhD / Waitlisted (2/27) / Withdrew in early April Brown - Biostat PhD / They said I was on a shortlist and asked how likely I would be to accept an offer, I'm interpreting that as a waitlist (2/27) / Withdrew in early March Pittsburgh - Biostat PhD / Waitlisted (4/2) / Withdrew in early April Based on my profile and my lackluster LoR choices, this seemed like a really top-heavy list of applications to send out (I had some safety school applications sitting on SOPHAS in case I hadn't heard anything by mid/late January). As such, I wonder whether lots of schools just liked me as a quirky applicant, in terms of majors, classes, and maybe personal statement (I know at least one professor did read it, they brought it up apropos of nothing at a visit). Given that I didn't take the Math GRE subject test, in retrospect I might apply to Washington biostat instead of Columbia stat, and I also might replace CMU or Minnesota with UPenn Perelman since I like neuroimaging and CMU just seems really dang tough to get admitted to. As you can imagine, I'm very happy with the results of my application cycle, and given that many of my best offers are from schools that I didn't expect would like me, it's important to remember than your impression of a good fit/likely admission is definitely not the same as the schools' impressions thereof.

I'm just another applicant, and I'm unsure enough with this evaluation that I was pretty hesitant to post, but I can give it a (potentially inaccurate) shot. Your GRE scores and upper-Ivy League background will clearly help you a lot, and it probably doesn't hurt to have a good computer science background in both theory and practice. A 3.5 GPA isn't great, but I'm not sure how much it hurts you at an Ivy -- there's been some grade inflation issues at top private schools, but you're also competing against top students. If I'm comparing against myself, I don't actually know that your Real Analysis grade even hurts much -- I got a B in Real Analysis at a less prestigious school and had no math professors write letters for me, and still got into UNC biostat two weeks after I applied. I am assuming that you're doing more applied research, which ultimately doesn't mean that much, although it's still probably worth having your adviser for that write a letter of recommendation for you. I suspect the more learned members of the forum will correct my assessment later, but I would guess that you'd be competitive at biostat programs 4-10 (UNC through MD Anderson/UCLA level), with an OK but not great chance at the top 3. My reason for thinking you'd be competitive at 4-10 is that I thought I'd be competitive in that range, and clearly UNC thought so too. Meanwhile, you go to a much better school, should have similar GRE scores, and strong computation and coding experience that could make you attractive to higher-up programs even though you have a lower GPA/grades overall (for instance, Harvard biostat in particular seems to care a lot about numerical analysis and computing). That said, I have a couple questions. One -- what exactly does it mean to get "credit" for a course grade? Is that a C? Did you take this class as a pass/fail, and if so, was that required or did you choose that? If the latter, why? I'm super unfamiliar with taking actual academic classes and getting a non-letter grade for them (as you can tell), so I'm curious as to what an admissions committee would make of "credit" in a linear algebra class. If that's standard, then no problem, but otherwise you should definitely have that advanced linear algebra professor be a letter writer. The reason I make that sound like not just fait accompli is because if you have had a close supervisor with a stat/similar PhD or background at your job, you may want to consider them as a potential letter writer. I have no idea if that's the sort of place you work at, though, just something to keep in mind. For stuff you can do, I would say taking more proofs-based classes and getting A's or A+'s wouldn't hurt. Even so, I'm not sure how much you stand to gain by doing that for a year before applying -- you yourself note that the school in question isn't super highly ranked, and you have an Ivy League real analysis professor recommending you already. You shouldn't need to worry about getting involved in research beyond what you're already doing, nor would you need to (say) take a biology or genetics class -- you can learn that in grad school if you really need it. I have a hard time with this profile, because it seems similar to mine except with a lower GPA from a better school, plus better computation and work experience. That said, I also feel like I really overachieved my qualifications during this admissions cycle, so your results may vary.

Just to piggyback off of Zanelol's suggestions, my girlfriend has a disability that she works with her university on, and there's a lot more that they can be doing to help you with regarding your test anxiety -- different testing environments, proctoring, sometimes(?) allowing emotional support animals in to the test. She says that you often need to jump through some hoops to accomplish this, but you already seem to have a working relationship with your school's disability resource center, and your therapist should help you get the necessary documentation. Furthermore, talk to your professor about this. I have a relative who is a professor, and I know that they have administered tests fully orally to students who have issues with written exams. My girlfriend has also had good experiences working with her professors -- nobody wants students to fail or get low grades for reasons that aren't lack of understanding of the material. Also, I took classes over more than 5 years and several summers -- it isn't rare for grad school applicants to take that route, and if it's monetarily viable for you, you should consider it. Finally (as something of an aside), it looks like you might have used your actual name as your username. Just in case you aren't aware, you cannot really delete posts on this forum, so if you are hoping to preserve privacy about these topics in the future, you may want to consider changing your username on your profile/account settings page. An addendum, since I didn't address your questions: if there are any advisers or professors you really like at BC, they are probably better resources for major choices than we will be at a distance. Lots of people change majors, though, so if that is a consideration for you, then you shouldn't worry about having a meandering path. Music majors can do plenty of jobs, but you will have to explain to employers how your music skills will make you successful in that position (hard work, creativity, effective leadership, autodidaction, etc). As for your chances at music after college, the Fine Arts forum on here might be a good place to start, along with your favorite music profs. Sorry I can't be of more help, unfortunately these are questions that require more knowledge of you personally and non-math/statistics fields in general to answer satisfactorily.

That's an OK idea, but due to the editing times allowed on here, it may make sense to wait until closer to/after April 15th, to get a better sense of waitlist chances if nothing else. EDIT: It's a better than "OK" idea, I got a lot of benefit from looking at those threads too, but I also recall the editing issue cluttering up those threads in the recent past, hence my recommendation.

Just to keep folks updated, I've declined every program that isn't in North Carolina, so that's Ohio State and UCLA previously, and more recently Illinois, Wisconsin, and waitlist spots at Pittsburgh and Minnesota. I'm not planning on saying which of Duke stat, UNC biostat, or NC State stat I end up accepting (for privacy, since I'd like to help people on this forum in upcoming years), but I recall seeing people on the waitlist for all three places on this forum, so I'll try to make my decision as quickly as I can. For those with NC State waitlist spots, I just got off theirs this morning, so there may still be some chance for y'all if you hold on for a bit.

I'm just another prospective student, so keep that in mind, but if it's opinions you're looking for, I can certainly provide that. They're both really good schools, as you know. You are narrowing down what you'll be doing during your PhD program a little by going biostat instead of stat, but Johns Hopkins is good enough that I wonder how much you'd be narrowing your options beyond your PhD program. For instance, one of Duke's statistics professors got her PhD from Johns Hopkins. You might want to push for some measure theory background at Johns Hopkins, but I bet you'd do fine on the academic job market anyways, although you might skew more towards looking at biostat jobs instead of statistics jobs coming out of Johns Hopkins instead of Columbia. Your interest in stat vs. biostat faculty positions might inform your choice a bit -- I get the sense that biostat professors tend to be co-investigators on lots of grants, and support a lot of their salary through that sort of research (or at least, they do at Hopkins -- feel free to check out Roger Peng's podcasts, his perspective may be helpful -- since this is mostly about academia, I'm guessing The Effort Report would be more helpful). Meanwhile, it sounds like stat professors have more hard money, and have more teaching responsibilities and fewer collaborative research requirements. Being super open to research topics is a good and realistic position, but it does make it a little difficult to provide too many opinions. For instance, if you were interested in imaging research, I'd imagine it would be pretty easy to pick Johns Hopkins (along with many other research areas). I'm less clear on Columbia's research strengths, but I'm guessing from Gelman that they're strong in social sciences and Bayesian research amongst other strengths. Personally, I'd choose Johns Hopkins, but I'm particularly interested in neuroimaging and health applications, which makes it an easy choice for me. Without knowing more about how applied vs. theoretical you research interests are (or any areas of particular interest), I don't know that I can really prescribe either one as being better for you.

I don't have much useful input, but something to consider: are you looking more at industry, academic, or governmental jobs after you graduate? Columbus has Battelle, of course, along with a lot of banks since it's the state capital. I'm unsure about Gainesville/Florida's statistics job market, but I'm guessing it may be somewhat different. If you're looking for academic jobs, go with the strongest adviser/advisers in your chosen field, but I doubt your choice of adviser matters as much if you're looking to work in industry/maybe government.

Oh yeah, that seems fine from my perspective -- I've been checking on that too (although I'm not sure how much I'd read into that if I was a professor, but that's beside the point). My concern is pretty much entirely about asking about *my* specific chances, especially since I'd be concerned about accidentally decreasing my chances of working with professors by violating some part of professional decorum.

Hi everyone. I'm aware that it's considered largely pointless to contact professors about their research or whether they'd be interested in working with you before being admitted to programs. Generally, I have further assumed that I shouldn't really discuss whether a professor would accept me as an advisee until I've been in the program for a while, and am getting close-ish to quals -- granted, I might be accepted, but the professors still don't know much about me or my functioning abilities, and they don't even know whether I'll be around or leave with a master's or so on. A professor has suggested to me that as part of my graduate school choice, I should contact some professors of interest right now and gauge how open they'd be to advising me on my dissertation. This professor is in the statistics/biostatistics field and I have pretty strong regard for their understanding of academic politics, but this seems like a really forward strategy, and I'm concerned that professors would largely be annoyed by this sort of behavior from an admitted student. Is this something people do, and I've just misunderstood the previous discussions on the topic? Is this something that's coming up because some of the programs I'm interested in (notably Duke) only have 1 year before quals and adviser choice?