Profile Eval & School Recommendations: MS to Statistics PhD Fall 2021

[StatClaire]

Hi all,

Student Type: Domestic Asian Female 

My background is quite untraditional, and this will be my weakness to pursue a higher degree in Statistics. I finished my undergraduate studies abroad with a non-stem major. Then I took some math courses as a non-matriculated student in a state university. Currently, I am pursuing my master’s degree in Statistics in a top 20 statistics department. I plan to apply for a Statistics Ph.D. degree this fall. I would like to get some advice on school selection and how to improve my background.

Undergraduate math-related background:  From a State university
. Major: Non-matriculated (only took the following courses for the purpose of MS application)
. GPA: 4.0
. Math coursework: Cal I (A), Cal II (A), Cal III (A), Matrix Algebra (A), Multi-var Cal (A), Foundations of Modern Math (A), Real Analysis I (A), Intro to Diff EQ (A), Prob and Stats for Engineering (A)

Graduate: Top 20 Statistics MS
. Major: Statistics
. GPA: 4.0
. Coursework: Stats Programming I (A), Stats Inference I (A+), Stats Inference II (ongoing), Intro to Clinical Trial (ongoing), Applied Stats I (ongoing), Linear Models and Regression (next term), Applied Stats II (next term), Multivariate and Longitudinal (next term). Will graduate next Summer

GRE General Test:
Q: 165
V: 160
W: 3.5

Applying to: Statistics PhD
 

Edited September 12, 2020 by StatClaire

[Stat Assistant Professor]

How did you perform in your undergrad? Assuming you did well enough, I would say you have a very good shot at a top 20 Statistics (not Biostat) PhD program. The top 10 Statistics programs (i.e. University of Michigan and above) might be a reach because your math background may be a bit lacking compared to other outstanding applicants, but you could apply to a few of them and see what happens (you could get lucky). Just don't make your list of schools *too* "top-heavy."

Now, if you were to apply to Biostat PhD programs (and not just pure Statistics), you would probably be able to get into a top 5 Biostat program and definitely any program below the top 5. I know someone who got into Harvard Biostatistics with a non-traditional background similar to yours (they majored in Biology as an undergrad, but then took the prerequisite math courses and completed a Masters degree in Statistics -- and this was all *while* working full-time at a software engineering job, and their MS school wasn't as prestigious as yours either). 

Edited September 12, 2020 by Stat Assistant Professor

[StatClaire]

Thank you so much for your suggestion, @Stat Assistant Professor! It’s very helpful. Really appreciated it.

As to my undergraduate background, I have a double-major in Law and Accounting in my undergraduate school (from a foreign country, from 2006-2010, GPA for Law: 3.32, GPA for Accounting: 3.10). Comparing to my math courses, these GPAs do not appear appealing. ;-(

Other academic backgrounds: 
I got a Master’s degree in Accounting from a private university (ranking 100, from 2012-2013, GPA: 3.63).
The following year, I got a Master’s degree in Law from another private university (top 20, from 2013-2014, GPA: 3.28).

Non-matriculated math courses (from a state university, from 2017-2019, GPA: 4.0)

[Stat Assistant Professor]

Hmm, well, the GPA from a foreign university matters more in context than anything else. For example, at Indian Statistical Institute, students are graded out of 100 pts and it is almost unheard of to get over a 90... and anything over an 80 is considered excellent. If your alma mater is well-known for grade deflation, then it wouldn't be quite as big a deal. Do you know if this is the situation for your undergrad?

But also, you have a 4.0 in all your math/stat classes, and your earlier degrees are not that relevant to your current academic pursuits. So it's possible that adcoms might weigh your most recent academic performance more heavily. I would apply to a wider range of schools if I were you and make sure you emphasize the 4.0 in math/stat courses in your application. The fact that you are a domestic applicant also means you might be able to aim a bit higher than an international applicant with a similar profile as you should.

Edited September 13, 2020 by Stat Assistant Professor

[StatClaire]

Thank you so much for your comprehensive evaluation, which is really valuable for my school selections and PS writing. Yes, my undergraduate school is famous for grade deflation, especially for Law major. I would apply to a broader range of schools, as you suggested. Thank you again. ?

[Stat Assistant Professor]

10 hours ago, StatClaire said:

Thank you so much for your comprehensive evaluation, which is really valuable for my school selections and PS writing. Yes, my undergraduate school is famous for grade deflation, especially for Law major. I would apply to a broader range of schools, as you suggested. Thank you again. ?

You probably won't ask professors from your undergrad for letters of recommendation, but I would make sure that you ask at least one of your LOR writers to make this point about grade deflation at your undergrad clear. It might also be prudent to mention it as well in your statement of purpose,  just in case the adcoms are not familiar with the grading at your undergrad. Most Statistics PhD adcoms will be aware that a low 80 from ISI is actually very good, for instance, but I'm not sure if such familiarity will be similarly the case for your school. 

The non-traditional background should definitely be addressed in your SOP and letters, but of course, frame it in a positive light -- i.e. how you were motivated to change careers and study statistics, how you got all A's in math/stat classes, and how you are doing very well in a grad program for Statistics at present. These are all positive indicators of your ability to succeed in a Statistics doctoral program.

[StatClaire]

15 hours ago, Stat Assistant Professor said:

You probably won't ask professors from your undergrad for letters of recommendation, but I would make sure that you ask at least one of your LOR writers to make this point about grade deflation at your undergrad clear. It might also be prudent to mention it as well in your statement of purpose,  just in case the adcoms are not familiar with the grading at your undergrad. Most Statistics PhD adcoms will be aware that a low 80 from ISI is actually very good, for instance, but I'm not sure if such familiarity will be similarly the case for your school. 

The non-traditional background should definitely be addressed in your SOP and letters, but of course, frame it in a positive light -- i.e. how you were motivated to change careers and study statistics, how you got all A's in math/stat classes, and how you are doing very well in a grad program for Statistics at present. These are all positive indicators of your ability to succeed in a Statistics doctoral program.

Really appreciate your suggestion on LOR and SOP. I will present all these positive indicators in my SOP. I have a concern about my undergrad math courses. Are they enough in the scope to qualify for pursuing a PhD degree in pure Stats? If possible, do I need to take any other undergrad fundamental math courses?

[Stat Assistant Professor]

On 9/14/2020 at 1:36 AM, StatClaire said:

Really appreciate your suggestion on LOR and SOP. I will present all these positive indicators in my SOP. I have a concern about my undergrad math courses. Are they enough in the scope to qualify for pursuing a PhD degree in pure Stats? If possible, do I need to take any other undergrad fundamental math courses?

If you're planning to apply to pure PhD statistics programs, then I think you are okay with what you have. A proof-based linear algebra class might be helpful. Of course, more proof-based classes is always helpful insofar as they give you more practice writing proofs and mathematical reasoning (so you'll be well-prepared to take classes like measure theoretic probability, advanced inference, theory of linear models, etc.), but this is not strictly necessary.

If you aren't going to apply to very top programs, I think you're okay. Many PhD programs recommend that you can retake (non-measure theoretic) real analysis in your first year, in order to refresh your brain on proofs.

[StatClaire]

Thank you so much for the responses. It’s really helpful for me.