Ways to bolster application for PhD programs after graduation

[kingsdead]

Hi everyone, I graduated in 2017 and am planning on applying for PhD programs in statistics and biostatistics this year, for admission during fall 2020. I was just wondering if anyone has a sense of what I can do between now and when I apply to boost my chances for getting into top programs. Would appreciate any advice at all!

A bit about me: I have a decent math background (real analysis, measure theoretic probability, other upper level undergrad/intro grad level courses in analysis and algebra that are probably not very relevant to stats), mediocre CS background (a few courses where I haven't done too great), spent time after graduating working as a data analyst for a public health program, have a couple of math publications from an REU, and currently am in a volunteering program abroad. I'm done with the GRE + GRE subject test and am comfortable with the scores. I'm just wondering whether there's anything I could be doing right now to help my chances. Some more concrete questions:

1) I don't know much about stats (my background in school was very much pure math). In particular, I have no clue about potential research interests. What's a good way to go about learning more about potential research interests? How important is it to have informed research interests during application season?

2) Related to the first question, would it be worth spending time learning more stats before applying? I'm wondering about something like going through Casella Berger or other stats books to make up for the fact that I don't know much beyond a stats 101 type course. Ideally I'd take courses at a local university (I've read people suggesting similar things on this forum) but that's not an option for me given the fact that I'm living in a very rural part of the world right now, and will be here until summer of 2020, right before I hope to start school. Would schools care about me taking the time to go through such books? I'm probably going to do so regardless just because I want to learn more but I'm curious how schools would perceive it.

3) As I mentioned I didn't do too well in a couple of CS courses I took in college (B-, B+, etc). I posted about this a while back and some people commented that my experience programming as a data analyst should be enough to offset any potential concerns there. Would it be worth taking some courses on something like Coursera to show schools that I'm serious about improving as a programmer? Would they care at all about that?

Thank you all for listening!

[Geococcyx]

It looks like you've been around the forum for a bit, so I'm not sure how much other information I can give (especially given that I'm just another applicant), but if you'd like some allaying of your concerns, maybe I can still be useful:

1.  Most people don't really know their research interests that well at this point in their careers.  I had a few application areas, and maybe one vague theoretical area, that I expressed interest in via my personal statement, but you could probably get by with less (based on my experience at visit days), and as long as you aren't amazingly narrow, having more developed interests shouldn't really be an issue either.  I'll echo some responses to your previous posts and say the best ways to learn (aside from asking about specific schools on the forums, which sometimes works) are to look up some top professors at schools you're interested in and look at their papers.  You don't have to read the whole thing, but at least go through some abstracts.  Listed faculty research interests work too, although the quality of such postings varies pretty widely between departments in my experience.

2.  It wouldn't hurt to work through Casella and Berger, but if you have strong grades in real analysis, measure theory, and other proofs-based math classes, then I doubt it would make you look that much better.  I'd assume going through Casella and Berger would be more helpful in preparing for the grad program itself, rather than the application process.

3.  I don't recall such online courses really meaning all that much to admissions committees due to vagaries in their grading, so I doubt it would be an issue.  Frankly, plenty of people (myself included) are mostly at a loss with regards to computer science topics like algorithm design, software development, and whatnot, and generally it's not any sort of drag on our applications.  

It's a little hard to know how well you'll do without GRE scores (or at least SAT/ACT proxy measures of standardized test ability) and grades in your analysis/measure theory/probability sorts of classes, but if I had to guess you will probably have a quite strong profile -- maybe not tip-top level, but certainly stronger than mine, particularly if your math publications are in analysis or some area relevant to statistics.  I wouldn't stress it too much.  

Edited March 24, 2019 by Geococcyx

[bayessays]

1) If you go on faculty directories, sometimes it'll sort by interest. For instance, Bayesian statistics, causal inference, high dimensional data, met-analysis. Looking them up on Wikipedia might give you a base idea of the types of areas.  You could also start reading statistics blogs like Andrew Gelman's or magazines like Chance.  Reading papers is probably not the way to go if you don't have a stats background.

 

2) No. Have you taken any stats class though, even just a basic intro? That plus the probability you clearly have is all you need.

 

3) One B- in a non math class isn't going to hurt you very much beyond the general GPA ding. Don't worry about it and don't bring attention to it, but maybe emphasize if there are other places where you programmed in job or research.

 

You haven't listed your undergrad institution or your overall GPA, but I'm assuming they're both very good.  You seem like you're a great candidate for even top programs though. 

[Stat Assistant Professor]

If you have the math background, then you don't really need to take additional classes at a local university. This is only advised to do if you have no or a weak math background or if you need to take care of some prerequisites (e.g. real analysis) before applying. And you certainly have the requisite background if you've taken a bunch of proof-based math classes. A lot of statistics PhD applicants have backgrounds in pure math and are fine taking the Casella & Berger sequence with no prior background in the subject.

That said, if you have been out of school for some time, it would definitely be helpful to review some Calculus, linear algebra (including proofs), and basic real analysis before entering your PhD program. But since you are applying this upcoming fall, you have plenty of time. See these two threads for a suggestion of things to review (the below applies to both incoming statistics and biostatistics grad students):

https://forum.thegradcafe.com/topic/117420-general-reviewpreparation-prior-to-ms-biostats-program/

https://forum.thegradcafe.com/topic/117365-best-probability-textbook-for-self-study/

 

[kingsdead]

Thanks all three of you for your advice!

To follow up a bit with @Geococcyxand @bayessays, my GRE scores are 170Q/167V/5.0W, so I'm not worried about those. Forgot the exact score on the subject test but percentile was 82%... Maybe not good enough (given mediocre gpa) for Stanford, but I'm not planning on applying there anyway cause it's such a Longshot, and biostats programs don't require it anyway as far as I know. GPA was 3.75, definitely on the low end for top schools, but I did well in math classes (all As or A+ with a couple of A-) and also took a lot of math. And I did take a calc based intro stat course. I went to a liberal arts college, though for what it's worth it's considered a good one (think Williams Amherst Swarthmore Pomona etc). Publications were in number theory so not related (though analytic number theory... So I guess we used some analysis). One extra question I have, I see that a lot of fellowships etc talk about commitment to diversity and leadership, would something like Peace Corps service potentially help with that?

 

@Stat PhD Now Postdoc, thank you for posting those two links, very helpful. I have been out of school for a while so I will definitely review calculus, linear algebra, real analysis, and hopefully some statistical computing as well like R. 

Anyway, thanks y'all, and this forum in general, for answering my questions and being a great resource. I will definitely keep everyone posted about where I end up applying to and the results when the time comes. 

Edited March 25, 2019 by kingsdead