Advice for future MS Stats/Biostats applicant?

[Sopdet]

Hi everyone! I am a few years out of college and considering applying to masters programs in statistics/biostatistics within the next few years.

 

I am concerned about my inconsistent math record and my dearth of/low stat grades. For context, I have a general upwards trend in my GPA and my grades in Abstract Algebra and Math Stats were during one quarter where a close family member passed away.

 

Will I be competitive for good stat/biostat masters programs? Should I take mathematical statistics, probability, or linear algebra online or at a local university to make up for my current record? Additionally, if I were to apply for a PhD program post MS, how would my undergrad record affect my application chances for good programs? Thanks!

 

Undergrad Institution:  MIT/Caltech/UChicago
Major(s):  Math/Econ
GPA: 3.42 (Around 3.6 for major)

Type of Student: 
Domestic Asian male

GRE General Test: 

168Q, 163V, 5.0AW

Relevant Courses: 

Calc I-III (B-, B+, B-), Abstract Linear Algebra (B), Intro to Proofs (B-), Real Analysis I-III (B+, A, A), Measure Theory (B), Abstract Algebra I-II (C+, B+), Computational Linguistics (A), Mathemathical Statistics I (B-), Intro to Applied Stats (B+), Intro to Computer Science (A-, B, A), Econometrics (B+), Computability Theory/Formal Languages (A), A's in three econ with econometric components

Programs Applying: 

MS in Statistics/Biostatistics, interested in applying to PhD programs in the future but want to gain more research and stat background

Research Experience: 

RA for an econ research institute and for a business school professor

Work Experience:  

Data analyst for tech/consulting firm
Awards/Honors/Recognitions: Dean's List

Letters of Recommendation: Two letters of rec from economics professors, one from work supervisor with econ PhD

[Stat Assistant Professor]

With a degree from MIT/UChicago/Caltech, you should have no difficulty getting into any Statistics MS program with your record. These schools are known for both rigor and grade deflation, so you would probably also be a competitive candidate for PhD programs down the road. Ace your Masters program, and I anticipate you will have good luck with PhD programs as well..

[bayessays]

Yeah, you're vastly underestimating how valuable it is to come from one of those schools. You could get into a pretty dang good PhD program today.  That might be a good option to consider since you can get an MS on the way, paid for.

Edit: just realized you're interested in biostatistics. Even more so, your background is good. I'd recommend applying to top PhD programs now.  I think you'd have a shot at getting into a top 6 program now, and they'll usually consider you for the MS too.

Edited June 13, 2019 by bayessays

[Sopdet]

On 6/13/2019 at 2:23 PM, Stat PhD Now Postdoc said:

With a degree from MIT/UChicago/Caltech, you should have no difficulty getting into any Statistics MS program with your record. These schools are known for both rigor and grade deflation, so you would probably also be a competitive candidate for PhD programs down the road. Ace your Masters program, and I anticipate you will have good luck with PhD programs as well..

 

On 6/13/2019 at 3:40 PM, bayessays said:

Yeah, you're vastly underestimating how valuable it is to come from one of those schools. You could get into a pretty dang good PhD program today.  That might be a good option to consider since you can get an MS on the way, paid for.

Edit: just realized you're interested in biostatistics. Even more so, your background is good. I'd recommend applying to top PhD programs now.  I think you'd have a shot at getting into a top 6 program now, and they'll usually consider you for the MS too.

Thanks for the responses! I'm definitely surprised to hear that I'd have a chance for PhD admissions. Regarding PhD admissions, do most applicants have a good sense of their research interests and more stats research experience when applying? Does it make sense to go into an MS program to clarify research interests and hopefully improve my profile, or would it not make a difference to the admissions committees?

[Geococcyx]

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.  

[bayessays]

16 hours ago, Sopdet said:

 

Thanks for the responses! I'm definitely surprised to hear that I'd have a chance for PhD admissions. Regarding PhD admissions, do most applicants have a good sense of their research interests and more stats research experience when applying? Does it make sense to go into an MS program to clarify research interests and hopefully improve my profile, or would it not make a difference to the admissions committees?

It can make sense - getting high grades in a master's program improved my results the second time around, but it won't help because of research interests. I just don't think it's necessary for you to specifically apply to MS programs besides 1 or 2 safeties. I think a better use would be to apply widely to PhD programs since some programs will reject you because of GPA.  Your results will probably be a little unpredictable, but honestly, anyone who looks at your profile and thinks you can't complete PhD biostatistics coursework is stupid, and that's what they're really looking for.

[Sopdet]

On 6/19/2019 at 8:37 AM, bayessays said:

It can make sense - getting high grades in a master's program improved my results the second time around, but it won't help because of research interests. I just don't think it's necessary for you to specifically apply to MS programs besides 1 or 2 safeties. I think a better use would be to apply widely to PhD programs since some programs will reject you because of GPA.  Your results will probably be a little unpredictable, but honestly, anyone who looks at your profile and thinks you can't complete PhD biostatistics coursework is stupid, and that's what they're really looking for.

Do you have any suggestions on what range of MS programs I should apply to as "safeties" alongside PhD apps? Would Berkeley, UC Davis, or UCLA be reasonable options to shoot for with my MS applications? (Interested in these three because I have CA residency, but also open to going out of state.) Thanks for bearing with all of my questions!

[bayessays]

18 minutes ago, Sopdet said:

Do you have any suggestions on what range of MS programs I should apply to as "safeties" alongside PhD apps? Would Berkeley, UC Davis, or UCLA be reasonable options to shoot for with my MS applications? (Interested in these three because I have CA residency, but also open to going out of state.) Thanks for bearing with all of my questions!

I would personally be shocked if you didn't get into those programs.  An unfunded MS is not very competitive. A math major with an average GPA from Chicago is probably going to be the most qualified MS student at any program outside of Stanford/Chicago/Berkeley.

What could I tell you that would help alleviate some fear, since multiple people already said you are qualified for any MS program in the country?  Is it your GPA that you are worried about? Ignore it, you aren't being compared based on your GPA.  An average Chicago student is a known quantity - you are going to 100% be able to succeed in a master's degree anywhere, and that's all an admissions committee is going to care about.  

I just want to reiterate one more time that, unless you are extremely wealthy, I think applying for MS programs directly is a huge mistake.

[Sopdet]

18 minutes ago, bayessays said:

I would personally be shocked if you didn't get into those programs.  An unfunded MS is not very competitive. A math major with an average GPA from Chicago is probably going to be the most qualified MS student at any program outside of Stanford/Chicago/Berkeley.

What could I tell you that would help alleviate some fear, since multiple people already said you are qualified for any MS program in the country?  Is it your GPA that you are worried about? Ignore it, you aren't being compared based on your GPA.  An average Chicago student is a known quantity - you are going to 100% be able to succeed in a master's degree anywhere, and that's all an admissions committee is going to care about.  

I just want to reiterate one more time that, unless you are extremely wealthy, I think applying for MS programs directly is a huge mistake.

Yep, GPA is definitely a big part of my hesitation. Thanks for the advice!

[bayessays]

3 hours ago, Sopdet said:

Yep, GPA is definitely a big part of my hesitation. Thanks for the advice!

I completely understand. We have the exact same undergraduate GPA, me from a worse school.  I was very concerned, like you, and things worked out very well even at many top PhD schools.  If you had a 3.0, I would be more concerned about your PhD prospects.  Another reason I say to go straight to the PhD is because you probably can't prove much by going to a master's, unless you 4.0 at Chicago or Stanford.  Grade inflation is rampant in graduate programs, and since you already go to a top tier undergraduate school, moving to a lower master's won't help much (getting a 3.9 in your master's at Davis isn't more impressive than a 3.4 from your school imo).

It also comes down to your potential goals.  You seem to be unsure if you even want to do a PhD, so I am really weighing the potential waste of years of your life with your future undefined professional goals.  If you knew you wanted to be a professor at a top 10 school publishing theoretical papers in Annals, maybe you do want to take the risk and improve your profile as much as possible. You can also find a program (Michigan biostatistics and Iowa statistics come to mind) that initially will only admit you to their funded master's program, where you can, without stigma, leave after two years if you want. 

I hope this helps. I am mostly just stream of consciousnessing the things I'd be considering, so excuse the rambling. 

[Sopdet]

On 6/25/2019 at 7:21 PM, bayessays said:

I completely understand. We have the exact same undergraduate GPA, me from a worse school.  I was very concerned, like you, and things worked out very well even at many top PhD schools.  If you had a 3.0, I would be more concerned about your PhD prospects.  Another reason I say to go straight to the PhD is because you probably can't prove much by going to a master's, unless you 4.0 at Chicago or Stanford.  Grade inflation is rampant in graduate programs, and since you already go to a top tier undergraduate school, moving to a lower master's won't help much (getting a 3.9 in your master's at Davis isn't more impressive than a 3.4 from your school imo).

It also comes down to your potential goals.  You seem to be unsure if you even want to do a PhD, so I am really weighing the potential waste of years of your life with your future undefined professional goals.  If you knew you wanted to be a professor at a top 10 school publishing theoretical papers in Annals, maybe you do want to take the risk and improve your profile as much as possible. You can also find a program (Michigan biostatistics and Iowa statistics come to mind) that initially will only admit you to their funded master's program, where you can, without stigma, leave after two years if you want. 

I hope this helps. I am mostly just stream of consciousnessing the things I'd be considering, so excuse the rambling. 

Your stream of consciousness has been immensely helpful!

After thinking about this topic more this week, I realize another concern I have with directly applying to PhD programs is with my letters of rec. I expect one of my letters from a professor I did research with to be strong, but I get the sense that the other two (especially the letter from a work supervisor) may not be strong enough because the potential writers don't know me as well. Are there better ways than a master's to strengthen the LOR aspect of the PhD application? 

[Geococcyx]

My background isn't as close to yours as bayessay's is, but maybe I can be of some assistance via my own stream of consciousness (which turned out to be super long, sorry about that).  Keep in mind that I also have substantially less experience in this than bayessays and some other folks on the forums.

My personal opinion is that you'll probably have an easier time strengthening your recommendations by choosing different recommenders rather than by getting a master's degree.  Keep your strong letter from a research advisor, of course, but I feel like you have options to work with for the other two spots (or maybe 1 -- I don't know whether it's frowned upon to only have recommendations from professors once you've been out of school for a few years, although I personally doubt it would be a big deal).  I don't think people would worry too much about your math ability given your A's in real analysis, but it's not like it would hurt you to have a letter from one of your real analysis professors saying that you did a really good job in their class, or perhaps from your measure theory professor detailing how you improved from C+ work to A/A- work over the course of the semester. 

At the same time, having a breadth of math background gives you the latitude to choose a professor from a less mathematical background than econ for a letter if you want.  If you ended up taking a philosophy or literature class that you really enjoyed towards the end of your collegiate career, that professor might be a reasonable choice if you talked to them a lot and demonstrated creativity, analytical thinking, and good written or oral communication skills.  Your computational linguistics class might provide an opportunity like that too;  I'm woefully short on knowledge about that specific subject, but classes like generative syntax and similar linguistics courses make for great demonstrations of critical thinking, even if they don't seem super relevant.  One of my recommendations came from a genetics professor whose class I took despite it counting towards no degree or graduation requirement precisely because we spent a lot of time thinking about comparisons of models, how to infer causality, and that sort of gedanken work;  I'm sure the genetics background helped for biostatistics applications, but that surely wasn't the only useful information committees got from that letter.  I'm personally a fan of taking a few completely out-of-degree classes on a lark during your college career, and I think those classes can be great opportunities for letters of recommendation.  I find that taking classes in new subjects makes me more excited for that class, encourages me to develop more of a relationship with the professor through asking lots of questions, and will probably be in an area that many other applicants don't have experience in, which will help you stand out during the application process.  If you did that in college, great!  If not, the same thought process might apply to work -- maybe still have the Econ PhD write it, but you might point him to some experiences of good management, planning, and critical thinking on your part.  If nothing else, that might convince a PhD program that you'll be more disciplined than some younger applicants, and in a PhD program that's not a bad impression to make at all.  

Ultimately, I think you're too hard on yourself -- my recommendations were a research mentor like you, plus two professors that I'd had all of 1 class with each.  Those were small and talkative classes, of course, but coming from a large state school my baseline for a small and talkative class might still be rather larger and quieter than yours.  Choose folks who can say fairly unique and good things about how ready you'll be for graduate school regardless of the subject area, and then balance that with a need to have some research and math background testimony in there.  You almost assuredly don't need to go to a master's program just to achieve that.  

Edited June 29, 2019 by Geococcyx

[bayessays]

Absolutely agree with the above.  You're being way too hard on yourself.  Taking time off to strengthen your letters would be a complete waste of your time - a research supervisor or two, a work supervisor if they have a PhD are good, but get at least one quantitative letter.  You are going to be in the discussion at any PhD program outside the top 10, and you will already probably get into almost every biostat program, there is no need to improve your profile.  Improving your profile is only really worth it for people who went to unknown schools and/or really messed up their grades. You didn't do either of those, so your only paths to improvement are minor, and costly in terms of time and money. 

 

Edit: I speak first-hand as someone who did the master's at top school, with top grades and new letters, and my results were maybe marginally better after those improvements.  Your undergrad professors are among the top statisticians and econometricians in the world - can't some of them wrote you letters?

Edited June 29, 2019 by bayessays