Residuals

MLHopeful, you clearly have a strong mathematical background. May I ask why you didn't submit a 70% Math Subject scores to schools like Berkeley and Chicago? I would think that a 70% is very respectable score for a stat applicant. I do have a question that I have always wondered. Do you have a sense of how much weight is given to the verbal score on the general test? I am guessing not much.

I agree with your sentiments on a timed standardized test not being a true measure of a person's academic abilities. I can tell you of numerous stories of UG pure math students who get incredible standardized test scores on the math subject GRE but, in class, they are only "so-so" students. And there is the opposite, stellar and meticulous in-class students who just can't score high on the standardized test. To your original question, what is the threshold for submitting? Does one submit a 50-70% score? I told you of a case where a less than 40% score was submitted and he was admitted. Was he lucky in that the committee brushed it aside and looked at the rest of his record? We can't infer from a sample size of 1. It is a tough decision. What are you thinking of doing given whatever score you get?

This is one of the great mysteries when it comes to top stats departments. Math departments tend to talk about the GRE math subject test in terms of lower bounds (e.g., UCLA's math states that most applicants are at least 80%). Statistics departments are much more ambiguous. Stanford states that the average for admitted students is 82% but what is the distribution around that average? Chicago and Berkeley say the test is "optional" but encourage its submission. Students who do really well (say 80% or greater) will clearly submit. But, how many students score poorly and don't submit but get admitted in the end? Thus, we are dealing with censored data. But then I know of one Berkeley PhD graduate who submitted a math subject test score of less than 40% and was admitted. Berkeley clearly saw much more to this person's package than the score (coursework, letters, etc.). Berkeley was right in that this person did cutting edge research and has a successful career.

I doubt that Coursera will not be a sufficient substitute. Yes, go ahead with the proofs course and I suggest stating explicitly that you are aware that real analysis is valuable to have and that you are prepared to take the course upon admission (this is why you are taking the proofs course) if the department suggests so.

I totally agree with statbiostat2017. Stats and biostats programs generally have an expectation of at least real analysis I. So, if you can get that course, that would be helpful.

Ok, tell me how my comment is off the mark? You have no clue as to my background so I would suggest you chill.

I am with you cyberwulf. This is a strange post on so many dimensions. Yes, it oozes "arrogance" (everyone loves me, research experience can't be better, top coder, etc.). It is all good and dandy to have a confident attitude but this tone will be an immediate turn off. By the way, what does it mean that if we saw you in person, we would know you are a statistician? Seriously? That is actually quite insulting to statisticians. Recognize that top departments don't expect high-level of coding abilities. So, that skill is not a deal breaker. Good coding would play more well for a MS in data science application. Your poor math GPA along with so-so general quant GRE score is not suggestive of easily getting a high math subject GRE score. Put that aside, your general GPA along with with your weak math GPA would put you more realistically for a top 30-40 department.

What you have going for you is the UChicago reputation both in terms of being a world-class institution and in terms of the departments of math and statistics are top 5 ranked. The experience doing data-related work at Booth is also good to note in your application. Yes, UChicago is known to have lower GPAs but you still have the disadvantage of consistent B range grades both in math and statistics (as opposed to consistent A, A- with a B here or there). Also, the taking twice of Analysis III my be a subtle red flag. So, at this stage, it would be unlikely to land a top 5-10 department for a PhD. You state that you are interested in academia. The problem is that academia placement from statistics departments drops dramatically when you look at departments in the 2nd tier (go to a variety of departments and see their placement records; once you are out of the top 20, academia placement is far and few between). Thus, I would be very hesitant to just go to a top 30-40 department because you can at this stage (which you can given decent enough grades and from UChicago). With this said, I think you can leverage the UChicago background to get into a well ranked master's program (in math or statistics) and then use that as a stepping stone to a better PhD program n statistics. I am thinking schools like Wisconsin, Minnesota, etc.

Your answers are at the departments sites. Read below from Chicago statistics PhD admission. There is no worry about improving your scores: " We have no minimum for the GRE. Most applicants score above the 90th percentile of the quantitative section of the GRE. We are less concerned about the verbal and analytical writing sections. "

These PhD degrees in data science will not likely land students in academia (maybe lower-tier business school positions but for sure not statistics or CS departments). Looking at the UTennessee curriculum, there is nothing innovative except window dressing. Basically, they tossed in standard stats courses (probability, inference, multivariate, etc.) and then renamed operations research/operations management courses with trendy new names. Other than adding a research component and getting to say "Dr." at the end, I don't see these PhD programs as fundamentally better than most of the MS degrees in data science. I think it is a better strategy to pursue an MS at one of the brand names (NYU, Columbia, etc.).

You have more than enough for an MS in statistics. The need for real analysis and other heavy duty courses is more for PhD admission. Below is a copy and paste from the U of Chicago statistics department when it comes to MS vs. PhD prereqs: ================================== What are the prerequisites for the M.S. program? You should take calculus through the Jacobians and multivariate intervals, linear/matrix algebra, and elementary probability or statistics. For your reference, here is an example of an academic history that would satisfy our prerequisites. MATH 15100-15200-15300: Calculus I-II-III MATH 19520: Mathematical Methods for the Social Sciences MATH 19620: Linear Algebra STAT 23400: Statistical Models and Methods If you have met some but not all of the prerequisites, you are still welcome to apply, provided you are willing to stay in the program longer in order to take some background courses. What are the prerequisites for the Ph.D. program? You should have completed the M.S. prerequisites. Additional course work in mathematics, especially real analysis, and facility with computer programming are helpful. Substantial background, through study or experience, in some area of science or other discipline involving quantitative reasoning and empirical investigation may be considered in lieu of the specific course prerequisites. An applicant’s background in mathematics and in science or another quantitative discipline is more important than his or her background in statistics. =================================== Stanford has even less requirements for MS applicants than UChicago. Its site simply states: "Applicants should have successfully completed an equivalent of Linear Algebra and one other statistics courses to be eligible to apply."

I am not convinced that you will find many biostats PhD students with an MS in pure math. Actually, even with what I said of swinging too much to the left, I think a MS in biostats is better than pure math particularly at dedicated biostats PhD programs. Look at the backgrounds at top-ranked Hopkins: http://www.jhsph.edu/departments/biostatistics/directory/students/phd.html Mostly, UG in math or stats, then a smattering of MS biostats, MS stats, and MS applied math (vs. pure math). I think MS in pure math is overkill for biostats. I think also there is a subtle risk that an applicant with MS pure math to biostats might be viewed as a person who is applying also to stats departments and his/her application to biostats is a back up choice.

Math might be the best choice for a straight-up statistics department but I have heard that biostats Ph.D. programs don't see that much math as necessary (namely, beyond the UG sequences of linear algebra, analysis, multivariate calc, etc.). I think, however, an MS in biostats is a swing to the other direction of being not a sufficient foundation. I, personally, think an MS in stats is the sweet spot choice.

I don't think you should infer anything bad. It is simply very unusual to apply so early (on the heels of Fall 16 applications) and I think the director was just making sure of things. I assume that you are not taking any courses in the Fall of 2016 because it wouldn't be a good idea to apply now before new courses that the department would want to know about.

Depends on your long-term goals. Short-term going to UChicago would be quite costly. However, if one succeeds in its masters program then it is a good springboard to top PhD programs. The risk is that PhD students and masters students are taking the same courses so getting solid grades might be more difficult. NC State historically was a top program but since fallen to a second-tier program. But with that said, their is a legacy connection between NC State and SAS institute. The founders of SAS are from NC State. There is definitely favoritism for NC State students for possible internships and jobs at SAS which is an awesome place to work.

If you want to go for a PhD in statistics, then Chicago's masters program is better preparation. The curriculum provides a better foundation in terms of theory and span than Harvard's. However, if you are not interested in a PhD, then I would do Harvard. Harvard has strong connections for placing students in industry ranging from public policy to biostatistics.

I agree with Kevin Yeom in that Chicago and Berkeley lend themselves better to getting into a PhD in statistics. I would say Chicago's masters program is the most foundational in terms of future preparation. But beware that courses in Chicago's masters program are the same courses populated by the PhD students. So, it might present a challenge for getting top grades which will be critical for getting admitted into PhD programs.

UCLA's department of statistics is a good choice as a safety school. Housed for years in the math department to eventually become an independent department in the late 1990's. So, compared to the established departments at other schools, the department is fairly new. Accordingly, it is still struggling to get an identity and recognition. Not sure one should pick UCLA as the "go to option" if one is hoping for landing an academic position; the department simply doesn't have the reputation for that type of placement on a consistent basis. But, with this said, it is not a bad department. It just seems to fall in the safety school category. I am sure with time and the resources and new hires, the department has a positive trajectory moving into the future.

Might consider Northwestern's MS in Analytics: http://www.mccormick.northwestern.edu/analytics/ Columbia also has a master's in data science.