bayessays

If you want to go to a top 10 program, obviously more research and classes can only help. But your current coursework is fine (stats grad school is not like math where you have to have graduate level courses) and it is not like machine learning/CS grad school (where you have to have publications). If you still have time to apply this year (obviously not possible with some deadlines), I'd recommend just applying to a wide range of schools in the top 30 or so (and top 10 biostat), and if you aren't happy with the results, getting a master's or getting some more research experience.

This is mostly a statistics forum, so I'm going to give this advice from that perspective. You're already in good shape for statistics. (You probably are in decent shape for applied math, but you definitely have some gaps for a math PhD applicant.) You say you don't have proof-based math courses, but you *will* have Real Analysis after this semester - I'd prioritize getting an A in that, and your math background will be totally fine. (RA + Linear + Abstract Algebra seems like a heavy load in one semester, so if you have any flexibility, I'd just make sure you can devote the time to do well in RA). I realize it's already extremely late in this cycle, but you could apply to stats PhD programs right now. You'd also be a great candidate for top 10 biostatistics PhD programs. Especially after completing RA and if you're able to start doing research later this year with a Harvard stats prof, I see no reason why you'd need to get a master's before your PhD. I would just take a year off of school and re-apply.

Obviously your profile is outstanding, and your list is full of reaches but they are reasonable to apply to. Your Strong/Reach/Neutral categories are all basically the same level, and then there's a huge gap to your safeties (Pitt and GWU especially). Why not apply to a few more schools in the range of Texas/TAMU/PSU/Ohio State/Illinois?

I realized you said you didn't take the GRE, so maybe you can't apply to some of these schools. In that case, if you have to leave your list as-is for this year, then you can always just figure out something to do for a year if you don't get in anywhere - yes, this could be research or an industry job, but it could also just be anything that you enjoy (depends a lot on your financial situation, obviously, but it won't be that hard to find a job that pays the same amount as a PhD program). Taking a year (or two, or five) is not a big deal.

Your anxiety and self-criticism is jumping off the screen. Please take a deep breath. I hope you talked about yourself more positively in your applications, because you have a great profile. Yes, your list is top-heavy, and you should add more schools in the range of Rice (TAMU, Ohio State, Illinois, etc are great). If you're interested in Bayesian nonparametrics, why aren't you applying to Texas and Duke? It's only November 22nd. You can send out 5 more applications and you'll be in great shape.

Sounds like you understand the pros and cons pretty well. I don't see anything in your post that makes me think you really want to be a statistician or even study statistics more. Having an undergrad degree in statistics is not a reason to go to grad school for stats.

I think your profile will look a lot better when you have As in real analysis+probability on your transcript and that will be enough math. You can overcome the undergrad grades - I think people will actually be pretty understanding, but it's hard to evaluate your math ability when there's just so few classes right now. I know you don't have a lot of research, but I also think people will find your CDC/health experience interesting. I'm not suggesting that you apply to bad programs, or that you don't apply to top 10 schools at all. But I think Pitt/Emory/Vanderbilt/Duke/Iowa level is respectable and you should consider more schools in that range.

Even with your experience, PhD programs are going to value math training very highly, and you are facing an uphill battle with the low grades and online courses. Pitt is the lowest ranked school on your current list, but I really it should be where your list starts (#18 on US News Biostat rankings).

I agree with your recommender that you can definitely apply for PhD programs. There's no glaring weaknesses in your profile. You could apply to top 10, but I think 11-35 on US News is probably your sweet spot along with any top 10 biostat program. If you really want to go to a top 10 stats PhD, you could definitely improve your profile if you aced a top MS program and got some more research experience, but I think you can get into some schools right now that would set you up well for an academic career.

Why not just apply to some PhD programs and a couple MS programs as backups? It's the same amount of work. Your math background is good, but you have no research experience, so I have a hard time seeing you getting into a top 10 program at the moment. A MS that allows you to get some research experience would help a lot. But why are you so set on top 10? Top 30 programs are all fantastic for 99% of applicants.

No, I think stats/math/mathematical CS letters will be viewed similarly by most people. You didn't have much positive to say about letter writer 1 - does he know you well? Is the research you did with him a huge part of your SOP? You already have 2 letters from research advisors, so I personally think it's totally fine to have a third letter from a math professor who knows you pretty well and you know will write something nice.

I think all of your thoughts are spot-on. 2,3,4 seem like the best letter writers. You can definitely apply to any top statistics program, and I definitely agree that you don't need to apply lower than UT/Rice range. (Don't know anything about OR)

If GRE is optional, I probably would not send math scores below 165. I don't see much of an advantage to taking the math GRE if the school doesn't require it - I bet most people don't even know how to interpret the scores. Obviously if you can get a near-perfect score, it would probably look good, but if your math grades are good, I'd let them speak for themselves.

1 and 4 sound like easy choices. There's not a ton to go off of for 2/3 - applied math is closer than biomedical engineering probably, but basically you just want somebody to write a nice letter that you're able to work independently and are smart, so whoever you think is more likely to do that.

If you don't want to actually study economics, I think an economics PhD sounds like a painful journey. I personally think even going to a biostatistics programs can potentially be a bad choice for someone who isn't interested in doing medical stuff, so this sounds like a more extreme version of that. One thing I would consider is looking into how many econometricians are actually doing cutting-edge research in the topics you're talking about. My suspicion is they're mostly only at the top econ programs which are extremely competitive, so I bet you'd have way more choices of good-fit programs if you choose statistics. There is almost no chance you will get better causal inference training in an econ program than going to a stats PhD program with a good causal inference group. You can work with interesting data in any stats program. Are you sure the econ job market is that much better? Personally, I could only imagine doing the econ PhD if I was excited about being an economist. It really sounds like you want to be a statistician.