Stat Assistant Professor

Absolutely agree. Just to clarify: I think the OP should consider the programs I mentioned as in the "lower end" of the range of schools they should apply to. I believe they can get admitted to a top-tier program like University of Washington.

Your profile is actually pretty good. With a 3.9 in a math-y major from UC Berkeley, you should be in really good shape if you take a bit more math. I would recommend taking a few more math courses like numerical analysis and optimization, instead of econometrics or more statistics courses. For Statistics PhD programs, mathematical preparation is far more important than having taken a bunch of undergraduate applied stat courses (in fact, a not insignificant number of first-year Statistics PhD students have never taken a probability/statistics course before enrolling). Admissions is very competitive at the top Statistics PhD programs, so it would be good to apply to a semi-wide range of schools. But if you do well in real analysis, I could see you getting into a school like TAMU, Purdue, or Penn State (and you could likely get into a higher ranked school as well).

I think research experience does help the application a bit insofar as you can possibly get a good recommendation letter out of it. One of the posters on this forum is an international student from Australia who was admitted to Harvard, Duke, and University of Washington Statistics, and they had experience doing applied statistics in public health/epidemiology research (however, they *also* had a ton of math from a top university in Australia). You probably wouldn't do methodological/theoretical (bio)statistics research with a Stat/Biostat professor unless you are a PhD student in stat or biostat. But as a Masters student, you could definitely do some applied/clinical research and get a good recommendation letter out of that. That said, having more math is much more important. So if you had to choose coursework vs. research, I would prioritize taking more math classes and getting good grades in them.

Scoring well on the math subject GRE is sometimes helpful for someone with a non-traditional background like yourself. But it wouldn't be *nearly* as helpful as getting a Masters (or just taking advanced math classes at a local university as a non-degree seeking student) or some research experience. The majority of international applicants have high scores on the subject test, and yet, a lot of them are shut out of top PhD programs in Stats. And I believe one poster (also international) on this forum was also a non-traditional applicant who got research experience while working on a Masters at Harvard, and he was admitted to Statistics PhD programs at Harvard, Duke, and Berkeley -- even without submitting the subject test score. So the subject test is by no means sufficient NOR necessary to get into a reputable PhD program in Stats. I don't see that you have taken real analysis or any upper division proof-based math classes besides discrete math, and your math background will be considerably lighter than the most competitive international applicants. So I would recommend that you work on strengthening your math background and seeing if you can get some research experience rather than preparing for the math subject GRE. A Masters would help you do both of those. (Note: by "research experience," I don't mean that you need to be publishing first-author papers in stat journals -- the PhD program should train you to do that. But you could volunteer some time to collaborate on a project with an established professor, so you can get a good letter of recommendation speaking to your "research potential").

The job market for postdocs should remain somewhat robust (hiring is still allowed at a lot of schools as long as it’s funded externally, e.g. through grants). But the academic job market for tenure-track positions will be a lot tighter for a few years. For this reason, I would recommend anyone trying the TT job market to give themselves a deadline on how long they are willing to be a postdoc before moving on. I am actually serving on the hiring committee for my new department this fall (although most have instituted a hiring freeze for this upcoming AY, a few places are still hiring), so I will be able to give more insight into hiring from “the other side” by next spring. However, based on personal experience and what I’ve observed from other job market candidates that I was competing against: For Stat and Biostat, having a strong publication record is the most important thing for getting shortlisted for TT jobs at research universities. Having at least one paper in JASA, JRSS, Annals of Statistics, Annals of Applied Statistics, Biometrika, Biostatistics, and/or Biometrics seems to help a lot. If you are in a niche field like statistical genetics, then publications in the top field journals like AJHG or Nature Genetics will matter more. Thus, if your aim is to obtain a postdoc before trying the TT market, it is very important to choose a postdoc supervisor/lab group that has a strong RECENT track record of publishing in quality journals and a strong RECENT record of obtaining external funding and placing postdocs/PhD students in good academic positions. That way, you will also be able to gouge if they are working on topics that are of current interest to the stat/biostat community. It is also extremely helpful to get letters of recommendation from renowned professors. If someone on the hiring committee knows your PhD/postdoc mentor or one of your letter writers, it can go a long way. That’s also why it is advisable to do a postdoc at a prestigious institution if you can. Note that this applies mainly to jobs at research universities. It’s a little bit different for jobs at primarily undergrad institutions and Masters-only regional schools. Here, teaching experience will be more highly valued, and your job application needs to demonstrate that you understand their teaching mission.

As I understand it, UK programs have a strict deadline for how long a PhD student can receive guaranteed funded (four years max -- if they take more than four years, then they have to self-fund). Even in the U.S.A., I think it would be perfectly reasonable for someone with a previous Masters who skips the first-year courses to finish a PhD in four years. Students at Duke routinely finish in four years. This also depends on your goals, though. If your only goal is to finish and get an industry/non-academic job, then you may not have to worry that much about publishing and can focus on just getting the dissertation done. Then it would be reasonable to finish in four years. If you are interested in an academic career, then it may not be advisable to to finish that quickly, because you need publications to be competitive in the academic job market and publishing can take a long time. Some students will stay in their PhD longer just to get more publications on their CV. In my PhD program, one of my cohort classmates could have easily graduated in 3-4 years, but he stayed for the whole five years so he could get an Annals of Statistics paper on his CV. He then spent his fifth year on the job market and ultimately got a sweet TT job at University of Minnesota. The students I know who already had Masters degrees but took five years either: a) repeated the Masters-level coursework, or b) wanted to pursue academia and opted to spend a fifth year in grad school so they could go on the job market in their fifth year.

Like @bayessays mentioned, it will probably be program-specific. But I do know that a lot of programs, you have the option of taking the qualifying exam upon arrival if you already have a Masters degree. This is true for University of Michigan, NCSU, and University of Florida, for instance (I know students at these programs who already had Masters degrees and took the first-year exam before the start of their first semester in the PhD program -- if they passed the qualifier, they were allowed to skip the first-year classes). I think this is likely the case at a lot of other schools as well. However, you probably can't skip all the coursework entirely, so you would still need to take the second-year classes and some electives. Some very elite schools (like Stanford and UPenn) start off their first-year PhD students in measure-theoretic probability and advanced statistical inference right away, so they don't even start with Casella/Berger. However, the students they admit are typically fairly advanced and have already taken Casella/Berger or measure theory before entering. But the majority of programs would start off with Casella/Berger and not introduce measure theory until the second year.

I don't have firsthand experience with this. But I co-authored a paper on spatio-temporal statistics with a friend who got a Masters in Statistics and then earned his PhD in Agricultural & Biological Engineering with a concentration on spatio-temporal statistics. He is doing very well now, working as a Senior AI Quantitative Researcher at the Climate Corporation (he also interned there as a geospatial statistician the summer before he went to go work there full-time). Since he had a Masters in Stat already, he was able to complete his PhD in four years. I'm sure that you would be well-positioned to do so as well if you can bypass having to repeat Masters-level courses. I would look at the job requirements for jobs that interest you. If most of the job descriptions say "PhD preferred," then it might be worthwhile to go straight to the PhD. If you decide to go into industry in your final years, you can always do another internship the summer before you graduate. I would also assess how important it is for you personally to earn a PhD. If this is very important to you, you should go straight into it from your Masters. If you're on the fence, it might be better to go make some money.

OP: Assuming you did well enough in your undergrad and are performing well in your current math classes as a non-degree seeking student, you can probably get into a pretty decent Statistics PhD program, even without the Math subject GRE. Tbh, the math subject GRE isn't very useful or indicative of anything in most cases (it tests on subjects like abstract algebra and topology that are pretty much useless for Statistics). I think only Stanford requires it, and I think they mainly use it as a screening tool since they get so many outstanding applicants. On the other hand, if you want to get into a CS program, you're definitely going to need research experience and preferably at least one second-author conference paper. To be competitive enough for PhD admissions in CS, you would probably need to either work as an RA in a lab for a year, or get a Masters in CS where you do some research on the side for a professor, in addition to your coursework. You could bypass the Masters and research experience completely by mainly applying to Statistics PhD programs (especially ones where there are faculty who hold joint appointments in both Statistics and CS). Given your interests, you could do very well in a Statistics department that has faculty working in those areas. Columbia (Dave Blei), UC Berkeley (Michael Jordan), and University of Michigan (Jeff Regier) come immediately to mind.

There are also the NRC rankings: https://www.chronicle.com/article/NRC-Rankings-Overview-Applied/124704 It's best to think of rankings in any field as approximations for prestige (outside of the top 1-3 or so programs). For Applied Math, NYU Courant and UCLA really are in a league of their own. For Statistics, Stanford truly is the best in terms of research output, number of prominent faculty (some in their 70s and 80s who are STILL very active in research, e.g. Efron and Diaconis), and academic placements. But below that, you could probably make the case for swapping a few programs here and there, moving a few programs up or down, etc. Overall, I wouldn't be surprised if these rankings you've linked to are a pretty good approximation for prestige, though.

Rutgers is a very solid department, with some excellent professors like Cun-Hui Zhang (very famous) and Zhiqiang Tan. Some of their recently hired Assistant Professors are also very impressive, e.g. Zijian Guo and Pierre Bellec. It seems like the vast majority of PhD graduates from this department go into industry, but that may be because they have a preference to stay in the greater NYC region.

It is actually extremely difficult for international students to get into top biostat programs. The funding structure there favors domestic students (often times, funding in biostat comes from things like NIH training grants, whereas Statistics departments will fund a lot of their students through TAship in undergrad statistics courses; there aren't usually a lot of undergrad biostatistics courses). There are, in general, fewer American students looking to get PhDs in Statistics (there are a lot more pursuing only Masters degrees). So that is partly why it is somewhat less competitive for American applicants to PhD programs.

Your Masters degree should help for some schools, if you get really good letters of recommendation that can make the case that your mathematical abilities -- and your "research potential" -- are much stronger than your undergraduate record would suggest. I would suggest meeting with your letter writers and ensuring they can fervently make this case. That said, I don't think UPenn is very realistic when this program only has 5 students matriculating every year (and at most 2 are domestic). For elite programs like this, not even a Masters degree will be able to compensate for a weak undergrad record. A more practical "reach" might be NCSU. It would be worthwhile also to try larger programs like Iowa State or TAMU, who might be more forgiving of the lower undergrad GPA if you have strong performance in your Masters program. I'm not sure if UVA is a 'safety.' It seems like this program is somewhat selective. If you were getting rejected from schools in the tier of Ohio State before, then I think you should add more schools like Mizzou, University of South Carolina, and Arizona State to your list.

If you are interested in machine learning/high-dimensional statistics, don't overlook some of the top biostatistics programs. For example, University of Washington Biostatistics has some excellent faculty for this, e.g. Witten and Shojaie. PhD graduates from good Biostatistics PhD programs that emphasize both theory and clinical applications are able to get jobs in traditional statistics departments (for example, Edward Kennedy at CMU Statistics has a PhD in Biostatistics and publishes a lot in the top stat journals).

Yeah, in Statistics/Biostatistics, students are accepted by the department, not into labs. Most PhD students don't pick their advisor until their second year in the program at the earliest. So it isn't really beneficial to e-mail professors, even for prospective PhD students (most of the time). In fact, a lot of Stat professors now have notes on their websites that state that they "unfortunately cannot respond to inquiries from students who have not yet been admitted."

I think that even if you obtain a Masters degree in Statistics before applying to PhD programs in Stats, your profile is not competitive enough for top schools in Stat. If you perform very well in your MS program, you could aim for a few "reach" schools like University of Minnesota, Purdue, or Texas A&M, but I wouldn't aim much higher than those personally.

Unfortunately, I think top PhD programs in Statistics are likely out of your reach, and even a lot of mid-tier programs might be out of reach too. The competition for international applicants is extremely fierce. Although ISI is a prestigious university, I would think that many Statistics PhD programs will favor ISI students with *Statistics* Masters degrees over those in Quantitative Economics. If you want to try aim for Statistics PhD programs, I would recommend applying mainly to those ranked in the 50-80 range of USNWR.

Same as for Statistics PhD programs, see the thread below. Depending on how much emphasis the Biostat PhD program places on statistical theory in its curriculum, you can probably skip an extensive review of real analysis, though.

I think reviewing stuff from Calculus and linear algebra would be more beneficial, personally. Your review of Calculus need not be extensive (so you don't need to review stuff like washer and disk methods or any derivatives/integrals involving trigonometry, but you should definitely be comfortable doing stuff like chain rule, product and quotient rule for derivatives, u-substitution, integration by parts, change of variables, partial derivatives, etc.). For linear algebra, it may be helpful to review some things like linear independence/dependence, vector space, rank-nullity theorem, trace, determinant, eigenvalues, properties of symmetric positive-definite matrices, and projections onto subspaces. It may also help to review a bit of undergraduate-level probability and statistics, so you are already basically familiar with things like pdf, cdf, and certain probability distributions. Does the Statistics PhD program have a course on real analysis in their first-year curriculum? If so, I wouldn't bother spending a whole lot of time on this, though it may be beneficial to review it at a high level if you haven't taken a formal class in it.

Oop! Somehow I missed the part in the original post about the bridge Masters program also being fully funded. I would agree with @bayessays then that if you're virtually guaranteed admission to the PhD (conditional on academic performance) and think you can perform well in your courses, then UMich is an appealing option.

If you have a fully funded PhD offer from TAMU, I would be inclined to take that over a Masters from anywhere else.

Bingo. For my postdoc, I started working on semiparametric and time-varying models, which I had never touched at all in my PhD dissertation research. You can always switch your research focus later after your PhD (if you decide to stay in academia). Another one of my PhD advisor's former students did small area estimation for her dissertation, but then she changed her area as a postdoc and is now a world-renowned expert in the area of record linkage (at a top school, I might add). The PhD is more about learning *how* to do research than it is about a specific topic. Once you master that and figure out the best system that works for you personally, you can teach yourself most things.

Agreed that if spatial statistics is your interest, then Mizzou would be a good choice if you can work with Wikle and Holan. I know of a few Assistant Professors at decent schools (Florida State, Colorado School of Mines, etc.) who were postdocs at Mizzou and were supervised by these two. I actually think that some mid/lower-ranked statistics programs may provide more opportunities to work on spatial and environmental statistics. For example, Colorado State, Ohio State, and Missouri seem to have more faculty working on these areas than some of the "top" schools. This might be because spatial stats is a research area more concentrated in a Biostat rather than Stat dept at "elite" schools, though.

I wouldn't worry about this. You have a perfect GPA and a double-major in math and physics from one the best schools in the entire world, plus research experience in physics. I think adcoms will give a semester of P/F a pass (if you are worried about it, you can ask one of your letter writers to clarify the situation, and you yourself can make note of this in your application, e.g. the SOP). I would be surprised if you didn't get into several top Statistics PhD programs.

As long as you don't burn any major bridges, there shouldn't be any issue with leaving your program. I wouldn't worry about what other people think, e.g. whether or not they would be "disappointed" if you left. Most likely, if you are cordial about it, you can still use your professors as potential references for future jobs (though you probably won't need to resort to this if you have an industry job...). It's far more important to consider how YOU would feel if you exited. The main questions I would ask yourself are: how much will you regret it or feel like you're "missing out" if you don't earn a PhD? Is the PhD really necessary for what you want to do? Or even if it isn't necessary to achieve your career goals (seeing as most PhD's end up leaving academia), will earning a doctorate enrich your personal well-being?