2022 PhD Profile Evaluation

[blueberry-pi]

Applying for PhD in statistics/biostatistics after working in industry for a few years as a Data Scientist - would appreciate any thoughts, feedback, or advice on programs below given profile/research interests. 

Undergrad Institution:  US Top-5 in Statistics
Majors: Statistics, Applied Math
GPA: 3.91
Type of Student: International Male
Math Courses (All A's): Real Analysis, Complex Analysis, Linear Algebra 1/2, Abstract Algebra, Numerical Analysis, Differential Equations, Calculus 1/2/3, Discrete Math
Statistics Courses (All A's): Stochastic Processes, Time Series, Experimental Design, Linear Modelling, Data Science 1/2, Probability Theory, Statistical Computation
Computer Science (All A's): Algorithms, Machine Learning, Deep Learning, Databases

GRE: 168 Q | 163 V | 5.5 W

Research Experience: 2 years in applied statistics (3rd author publication in lower-tier journal - did most of the coding), 1 year in sociology (no publications - mostly database management)

Work Experience: 3 years as Data Scientist at large tech company

Recommendation Letters: 2 from research advisors (strong letters), 1 from professor with multiple classes and strong performance (mediocre letter)

Coding Experience: Python (expert), R (experienced)

Research Interests: Causal inference, applications to social sciences (specifically education/public policy), applications to public health policy

Programs Considering:

• UC Berkeley Stats PhD
• Harvard Stats PhD
• CMU Stats PhD
• UCLA Stats PhD
• UC Santa Barbara Stats PhD
• Harvard Biostats PhD
• Penn Biostats PhD
• Brown Biostats PhD
• MIT Social & Engineering Systems PhD
• NYU Data Science PhD

Are there programs here which don't sound like a great fit with my interests and profile, or any not here which could be a fit? I recognize my list is a top-heavy, but I'm satisfied at my current industry job and would go back to school only for a relatively well-regarded program, with the end goal of tenure-track professor at a R1. 

Edited June 7, 2021 by blueberry-pi

[bayessays]

UCSB sort of sticks out as a school that's not in the same tier as the others and probably wouldn't serve your goals to be an R1 professor very well.  Is NYU data science because of Jennifer Hill?  I think the interdisciplinary programs are a little riskier than getting just the stats/biostats PhD but some of those programs are pretty cool too, so it's a tough choice there.

What about other programs that are ranked similarly to CMU, like Duke and Michigan?  I think there is some interesting social science research done in both those places.

[Stat Assistant Professor]

OP: You should also check out University of Washington. The PhD program in Statistics there has an optional track for Statistics in the Social Sciences. I know somebody who graduated from UW Statistics with a concentration in Statistics in the Social Sciences, and they ended up as a prof at an R1 school. FWIW, their research was on respondent-driven sampling and social network analysis, and they work a lot on applications specifically to health and public policy.

[blueberry-pi]

Thanks! Some really good points brought up above - agree UCSB is a bit of an outlier on the list, was included mostly due to personal preference around location.

1 hour ago, bayessays said:

What about other programs that are ranked similarly to CMU, like Duke and Michigan?  I think there is some interesting social science research done in both those places.

 

49 minutes ago, Stat Assistant Professor said:

OP: You should also check out University of Washington. The PhD program in Statistics there has an optional track for Statistics in the Social Sciences. I know somebody who graduated from UW Statistics with a concentration in Statistics in the Social Sciences, and they ended up as a prof at an R1 school. FWIW, their research was on respondent-driven sampling and social network analysis, and they work a lot on applications specifically to health and public policy.

I heard UW and Michigan had relatively more onerous coursework/quals frameworks (for example, Michigan has 3 probability course requirements), is that true to the best of your knowledge compared to the other programs on the list? Having been in industry for a few years I prefer programs with lighter and more applied coursework/qual requirements. On a separate note for Duke, I originally decided to eliminate it given personal location preference, although location would not be an issue for either UW or Michigan.

I understand there are a lot of factors involved, although was curious if you have any thoughts on what application outcomes for this list might look like given my profile? Again, I'm sure there'll be a lot of variance in decision outcomes from year to year, although it'd be helpful to know for example whether these kind of programs are realistic.

[bayessays]

You're reading the Michigan website incorrectly, they don't even require a single probability class and have one of the lightest course requirements now.