StatsG0d

Speaking as someone who has been to both campuses, they are not very different. Both are college towns existing only because there's a university there. Heck, both cities have the word College in their names. While it's true that College Station is more connected than State College, it's still 1.5 hours to Houston, and you're unlikely to actually make that trip often (unless you're a TA for their online courses which are offered in person in Houston, and the lectures are posted online). I don't think either of these programs have notable faculty in this area. Have you applied to / gotten into UNC biostats, Washington biostats, Harvard biostats, and/or NCSU stats? These are the places to be for working in this area IMO. I don't agree with this statement at all. Carroll (their most famous faculty member by far) doesn't really do Bayes. TAMU has a lot of faculty working in spatial statistics and for various reasons Bayesian statistics kind of is the standard in spatial. TAMU has a large diversity of research interests (clinical trials, genetics, spatial, nonparametric, semiparametric, econometrics, etc.). Both departments are very large and are pretty comparable in terms of prestige / diversity of research interests. Secondly, and you're not the only person on this forum and elsewhere making this mistake, Bayes is a paradigm--it's just a different way of thinking / conducting statistical inference. For example, there's deep learning, and there's Bayesian deep learning. One of the most utilized methods for ML in text analysis is Latent Dirichlet Allocation, and the method is fundamentally Bayes even though none of the people on the paper would likely classify themselves as Bayesian. It's totally OK if you think "I'll never be interested in Bayes stuff," but don't make the mistake of thinking that Bayes is a research area in and of itself. It can be, but it is not always. I agree with @whiterabbit and @bayessays regarding choosing a place based on one advisor. Honestly, you'll probably find that you'll change your research interests as you move about the program because you'll be exposed to new things and, suddenly, area X doesn't seem so exciting. I have many friends who knew nothing of genomics, took the elective, and then made it their entire dissertation because they loved it so much. It's good to have a good idea of what you might like to do, but it's also good to keep an open mind.

I agree there's not really a huge difference between the two programs. Historically, I think Wisconsin has been stronger, but they've lost a lot of good faculty over the last couple of decades and allegedly had funding issues recently. Between these two schools, I would say go wherever you feel like you'd be happier. I think the biggest strength PSU has over Wisconsin (and many other schools) is the large amount of electives that you can take (as @bayessays alluded to). The student culture at PSU is awesome as well (highly collaborative, not very competitive), although I have never been to Wisconsin so I can't comment on theirs. FWIW: Madison is probably the more interesting place to live as PSU is right in the middle of nowhere (which is why I opted not to go there, despite really liking the department culture/atmosphere). Madison, WI has about 250,000 people vs. about 45,000 in State College, PA. State College is about 2.5 hours to Pittsburgh and 3.5 hours to Philadelphia. If you don't really care much for city life, it could probably be a great place as there's a lot of hiking around the area.

For sure. I was unclear. What I meant is if you're sure you want to do causal inference, go to Berkeley because it's a central focus of their department (particularly biostats) and you get the advantage of the culture / higher rank etc. As a side note, Robins is great, but he still does very traditional causal stuff (IPW, instrumental variables, etc.), while van der Laan is focused on very modern stuff (lasso, nonparametrics). Also, the primary appointment of Robins is in epidemiology, so it's not clear to me if he's generally available. He's also in his 70s, and I can't imagine he sticks around *too* much longer. That said, he still regularly publishes in JASA, Biometrika, etc.

Michigan's department doesn't have as much theoretical training, so I think it's less of a concern. UNC offers a "math boot camp" for incoming 2nd year students that reviews linear algebra and analysis. If you've seen some stuff before, I think it's more than sufficient. IMO, the most important topics in real analysis for biostats are (in [approximately] increasing order of importance): Limits (epsilon-delta proofs, finding limit, showing limit exists) Sequences (boundedness, convergence, uniform convergence, Bolzano-Weierstrass, Cauchy sequences) Infinite series (showing a series converges / is finite, Cauchy criterion, absolute convergence) Continuity Integration (Riemann, Darboux, Riemann-Stieltjes) In general, real analysis is really about putting bounds on stuff. So if you can do that, you're in pretty good shape.

I think Berkeley is the clear winner if one of following apply: You are really interested in causal inference You care a lot / enjoy theory Otherwise, I'd say go wherever you feel more comfortable / interested. Personally, I like Berkeley's model (no quals, customizable coursework, etc.)

Having a supportive advisor and good working chemistry is really crucial to be productive IMO, and this should definitely be taken into account when selecting an advisor. A lot of students find having co-advisors, one junior and one senior, can be fruitful. Since you are considering specific advisors only at each department, the more relevant metric IMO would be where these advisors have placed students, not where the department as a whole did. Either way, both departments are incredibly strong and I don't think there's a bad choice to be made here. Go where you think you feel best about. Based on what you've said it kind of sounds like you've already made up your mind to go to Yale.

The question wasn’t what defines a department nor did I claim that purely theoretical statistics is the only thing that matters. The question was how far ahead is Stanford compared to the others. Do not confuse what I’m saying to think that Berkeley is a bad department, it’s just a far cry away from Stanford, but everywhere except for Stanford is. That’s the point of @bayessaysand me. Also, I would caution saying that Jordan is *the* leader in AI. AI is a broad field, and one of his students, Ng, who has also revolutionized AI, is affiliated with Stanford. I think it’s totally fair to criticize Stanford for its lack of diversity, but unfortunately that’s not how department prestige is determined. Moreover, the lack of diversity is a problem across the field—certainly not Stanford specific. Finally, to your point about a diversity of research areas (e.g. causal inference), this is a fundamental problem with rankings. See my comment above regarding Michigan biostatistics, which I think everyone would agree is the best place to do genetics research in the world. If a diversity of research areas factored into rankings, Purdue, TAMU, and PSU would be at the top every year simply by having huge departments.

Responding to the statements in bold: Finance companies recruit quants globally, not locally or regionally. I know people who have gotten full time offers for quant positions in finance from U Florida stats and UNC biostats. That should not be a deciding factor whatsoever in my opinion. I disagree that Chicago's brand recognition is not as good as Yale. They're very comparable I think. Yale probably gets mentioned more in media, etc. because it's Ivy League. U Chicago has the 4th most Nobel prize winners out of any school in the world (by comparison Yale is 11th). I agree that brand recognition is not as important for a PhD. I would go to U Chicago. Much more to do, equal prestige, better department, etc. I don't really see where Yale has an advantage at all. While I agree with @Stat Assistant Professor regarding the best way to evaluate is based on student outcomes, there could be a lot of self selection bias (such as what you are considering doing now).

The biggest deciding factor to me would be where you want to work post degree. If you want to work in the US, I think most people would say it's advisable to do a PhD in the US. Whether or not that's based on actual evidence I'm not sure, but I do think it's the consensus.

You really couldn't have made a wrong choice. Duke is a great place (maybe the best place) for Bayesian statistics (e.g., Herring, Dunson). Your stipend will certainly go further in Durham than Seattle. Best of luck!

If people disagree then it's just their ego talking. The people @bayessays mentioned have revolutionized the field. You will scarcely find a single person, let alone multiple, that have had the influence those people have had at most departments. I somewhat agree with this. I personally think Harvard's program is slightly overrated because they are lacking in theoretical training compared to Hopkins and (especially) Washington. It is true that outside the top-5 (UW, JHU, Harvard, UNC, Michigan), there's a huge drop-off, but I don't think anyone will argue that of those 5, Michigan is, by a substantial amount, the best place to be to do genetics research (and probably the worst place of the top-5 to do much of anything else). Similarly, I don't think many people would disagree that Harvard is the best of the 5 at causal inference. The other 3 are probably the best options if you're not sure what you want to do (which I think is the case of most people whether they are aware of it or not). UNC's main pull is that they have a faculty with largely diverse research interests, but I doubt you'll find anyone who truly believes their department is superior to UW / JHU in any way other than student paper awards.

Typically, they do not ask for grades. It is possible that they conditionally admit you based on a minimum grade. I expect a B+ would be sufficient if they ask.

This. With emailing, I found either they were receptive to it or just ignored the email, so there's high upside and basically zero downside.

TLDR: All those programs are pretty similar. If McGill is a sure thing, it's probably only worth it to apply to other places if you would for sure go there over McGill. These rankings might help (but they include OR so there's some noise). All of those programs are great. The ones @Casorati mentioned are all really good. I would put them in the same tier. Provided you get into at least two of these, I would say go wherever you feel you would be happiest. If it were my choice, I would say McGill simply for the location. Sure, it's cold, but so is West Lafayette, Urbana, and State College. At least McGill is in a large city and there will be a lot to do / easy to catch a flight somewhere. UNC is kind of a nice middle ground because while Chapel Hill is a college town, a major airport (RDU) is only a 20-minute drive, and Durham and Raleigh are both nice cities with quite a lot to do relative to their size.

I agree with @Casorati. Northwestern's program honestly is not great. Evanston is a really nice place and near Chicago so location it's awesome, but the program prestige is pretty lacking.

All of those programs are much more competitive relative to their respective rankings, so I feel like it's a waste of resources.

Based on your profile, I would only apply to the larger programs in both stat and biostat. Duke biostat seems like a waste, as does Yale and Brown Stat. You could maybe consider adding Emory and/or Pitt for Biostat. The former would be a solid target and the latter a solid "safety".

First, I think you'll have to specify which of these departments that you are applying to are stats and which are biostats. Second, I am surprised you list Pitt as a reach and McGill as a "safety," as McGill is arguably the superior department. Thirdly, I really think this is tough to judge. The D in linear algebra looks very bad, and normally I would say this would exclude you from any ranked stats/ biostats program. However, you've received top marks in graduate level math classes. It's unclear how adcoms will view this, and you should address it in your personal statement. Finally, if your advisor knows your situation (i.e., your performance in undergrad) and you are at an institution with a solid stats department, then I would say you can trust your advisor's opinions about where you have a good shot to get in.

I guess I would not submit it. You should note that Northwestern is highly competitive relative to its ranking due to school prestige.

I feel like the following schools are very high reaches for you: Carnegie Mellon, Berkeley, Stanford, Harvard, Chicago, and Washington. Of the remaining schools, some (more attainable) reaches would be Duke, Yale, and Michigan. The remaining schools sound reasonable as targets.

I think if you explain the drop in GPA on your SOP, you'll get into many of those programs.

I absolutely agree that you should apply to as many schools as you can afford. It's always best to cast a wide net, but many people tend to have financial constraints that preclude them from applying to more than say 7 schools. Michigan is worth adding only if you're surely interested in genomics. If you're not set on it, I don't really think Michigan is a good place to be. Their placements are great, but I feel this is more of a function of the fact that genomics is very hot right now, and UMich is probably the best in the world at it. I think the school list seems pretty reasonable. Again, I think that the Ivies will be tough, but I would be surprised if you weren't accepted to at least one of those programs. Also, I'll say that I don't think departmental prestige really matters much. There are benefits to being a big fish in a small pond--being the standout student, getting to chose whomever you want as your advisor, etc. So don't feel like you absolutely have to break into one of the best departments. I'm not saying that the rankings don't matter, going to a higher ranked department has its advantages, but it's far from a deal breaker to go to a lower ranked department.

Yes, I think you are aiming too high. This does not mean that you’re not a qualified candidate. You have a strong profile, it’s just that the average international student’s profile is significantly stronger. It has nothing to do with your degree but just your math background. I did not major in math or stat but still had several more math courses than you have taken. You have to put yourselves in the shoes of the adcoms and ask “should we admit this student when there are several students (both domestic and international) who have A+ grades in complex analysis, measure theory, etc. who also got a perfect GRE Q score. The reality is that international student admissions are very competitive. All else being equal, departments will prefer domestic students because they are cheaper to fund. That’s one reason why the competition for international students is so stiff. The letters may significantly boost your profile, but I still do not think you have much of a chance to get into a top-30 statistics program or a top-4 biostatistics year program (unpooled). I think you should ask your advisors where they think you should apply, mentioning that your math background is significantly shallower than both domestic and international students.

I think maybe Pitt would be a good option. NCSU would be somewhat of a reach, but they have some faculty doing research in biostatistics. As they are a larger program, there's a nonzero chance you could get in. Drexel (in Philly like UPenn) has a PhD in biostatistics, although I cannot attest to its strength. If your goal is industry, then where you do your PhD does not really matter all that much. GWU might be a good option if you could consider the DC area. They have PhD programs in both stats and biostats. In general, I think you should target the larger, more applied programs.

First, Yale, UPenn, and Columbia are not really in the same league as UNC for biostatistics, but the latter does not compute GPAs so it's fair to assume that you went to one of the former 3. Second, your math background is relatively shallow for an international student. Because of this, I do not think you have a good chance at either UConn or TAMU for stats. For biostats, I do not see you getting into Hopkins, Harvard, or UW at all. I think you have a slim chance at UNC. The rest of the programs on your list are considerably less theoretical, so you might have a better shot. However, the ivies on your list will be a challenge for you to get into because, despite their ranking, they are viewed upon favorably by international students who want the ivy prestige, even if it means sacrificing department/program prestige.