# Fall 2022 Stats MS application: Need some insight on my plan

## Recommended Posts

Hello,

I've recently come across this forum, and wanted to get some opinions on my grad (MS, not PHD) school application plan for Statistics. Would be great to get some opinions.

Undergrad Institution: Top 20 US News
Major(s): Applied Math and Statistics
Minor(s): None
GPA: 3.36 (Not counting non degree coursework done after)
Type of Student: Domestic Indian male

GRE General Test:
Q:
168
V: 162
W: 5.0

Calc 2 (B+), Calc 3 (B), Lin Alg (C+), Diff eq (B), Intro to Proofs (A), Probability(B+), Mathematical Stats (A-), Real Analysis 1,2 (B,B), Lin Alg 2 (A-),  Graduate Complex Analysis (B), Graduate Real Analysis (with measure theory) (A-), Numerical Analysis (A-), Time series (B), Advanced stats (B+), ML (B), Statistical Inference (A), GLM (B)

Courses (Taken post grad as nondegree at various schools in my area):
Measure Theoretic Probability (B) (Covid really messed this up for me here)
Abstract Algebra (A)
Graduate Lin Alg/ Matrix Analysis (A)
Functional Analysis and Optimization Theory (A)

Research:
One Capstone project as an undergraduate. Ended well, but it was a data analytics project with ML, not really statistics.

Other Experiences:
Been working as a business analyst since I graduated, so I am quite proficient with R/Python/SQL

Letters of Rec:
2 from Professors, one from my boss

I understand this is probably a weird profile. I was really undisciplined as an undergraduate and my grades aren't great. I decided I wanted to eventually end up at a PHD program my senior year during the capstone project and while taking graduate real analysis, because we spent some time looking at probability theory in that class and I was intrigued.

I began taking non degree classes in an effort to ameliorate my mistakes as an undergrad. I realize PHD programs are ridiculously competitive, so I am planning to do a theoretical MS first, redeeming myself, and applying to PHD programs. I'm trying to look specifically at masters programs that are more theoretical and allow me to take some PHD level courses. After having done Casella and Berger as an undergrad, I'm not happy about basically doing that material again as a masters student, but if that's what it takes....

Schools I'm considering (all masters in statistics, or mathematics and statistics):

US:
UNC, Penn State, UCLA, UCSD, Florida State U, U Minnesota, U Georgia, University of Maryland (College Park and Baltimore), UIUC, Perdue, GA state, Texas State, Ohio State, U of Utah, TAMU

Canada (Because money, but also mathematical rigor):

Edited by Frequentist0114
correction
##### Share on other sites

You'll probably get into all of those MS programs. In fact, I think you're competitive for any MS program in stats in the country, so take your pick.

You might be able to get into some PhD programs ranked 30-50 directly if you're interested in that. This is particularly true if your school is known for some type of grade deflation that would bring your GPA into some light.

While the GPA is somewhat low, you did go to a very good undergraduate institution and have a pretty broad math background. I'd be shocked if you didn't get into at least one stats PhD program 30-50 or biostats PhD program ranked 6 and below.

##### Share on other sites

Hey, thanks for the quick reply! I'm definitely more inclined towards biostatistics and might consider applying straight to doctoral programs. Seeing a lot of the profiles on here made me think I stood no chance without a masters degree first, so this is reassuring. My school isn't known for grade deflation per say, but the average gpa was around 3.4-3.5, though the math/cs average gpa was probably much lower.

I'm curious about the difference in chances between bios and stats. Why is that?

##### Share on other sites

Biostats programs just tend to have a shallower applicant pool, often with less of a math background.  Outside of the top 5 programs, your math background will stick out more there.

I think top 40 is a little bit of a stretch, but I think schools like FSU might be achievable for a PhD.  Depending on your goals after the PhD, it might be worth to apply to PhD programs now.  I think there are a lot of very good programs in the 40-70 range, but if you want to be a professor at a top department, you may personally find it worth it to get a top MS and reapply if you are willing to spend those extra two years and whatever amount of money.

##### Share on other sites

22 hours ago, bayessays said:

Biostats programs just tend to have a shallower applicant pool, often with less of a math background.

Yep mostly this (although I do feel like this has been changing in recent years). The top-4 programs are known to be pretty mathematically rigorous. Perhaps not as much as stats departments, but much more than the rest of the bunch.

I think there are some schools that will automatically consider you for MS admissions if you don't make the PhD. You could target those schools. Also, a lot of the programs have a process for internal PhD applications (e.g., I know UNC does). So you could also apply for an MS at a program where you'd like to do a PhD and see how that goes. I feel like that's a better option than applying to MS and then applying to PhD because you'll spend a lot of money in a 2 year MS program.

##### Share on other sites

For Phd programs, I think what worries me most is the B in graduate level probability theory as a non degree student. Covid got in the way at work and forced me into a situation where I couldn't study much...that, coupled with the fact that the class was graded harshly did not work out in my favor (most students, who were PhD math students got Bs looking at the class metrics on the exams). However, I understand that adcomms see Bs like they do Cs in undergrad. Is that not an immediate deal breaker? I'm not asking about the absolute top programs since my goal is not academia.

Edited by Frequentist0114
##### Share on other sites

I think if you explain in your statement of purpose the reasoning behind the grade it's definitely not a deal breaker. I think adcoms know/understand that it's difficult to learn in a virtual environment.

## Create an account

Register a new account

×