CS vs Stats vs Applied Math vs OR+ profile evaluation

[jdoe192]

I am a little all over the place. First here is my profile:

 

Graduated from a top 100 school in the US with a double major in stats and econ GPA 3.98 (dont know what the rankings of the 2 depts are ). During my undergrad years I always thought that i would go on to do a phd in econ which is reflected in my choice of classes. i'm aware that i lack so many classes so guidance on what i need to take is appreciated too!  Got  A's  in all my classes except for intro to probability (I KNOW, ah. freshman year) and took vector calc pass/fail. other than that took:

 

1-calc 1 through 3 (A)

2- calc 4 (P

3-linear algebra (A)

4- Regression analysis and variance (A)

5-intro to stats (A)

6- design of experiments (A)

7-Applied econometrics (graduate class using Stata, A)

8- Fundamentals of Math (math induction, proofs...etc: A)

9- statistical computing (SAS, R:  A)

10-into to probabilities (B+)

11- intro to CS (Java: A )

 

currently taking Real analysis , expecting an A. 

And obviously a bunch of other econ classes.

Programming languages in order of competency:
1-Stata, R (tied)
2-python
3-Java. 

 

Graduated and working as an RA, where my job is really heavy on the computational side 
So far published 2 papers, one in a big journal and the other in a decent journal (sorry im not giving their names away, dont want to be too detailed here!) 2nd author on both. both use advanced methods, like ML and network analysis.  I have really good recommendation letters from Harvard professors (Like REALLY good) one is from the Econ dept and the other is from Biostats. 

the tricky part: im not so sure which program fits my interests best. im really interested in big data and data mining, so something that is computationally intensive but at the same time applied to social sciences (not crazy on epi stuff, that's why im not too excited about biostats). I know that CMU has a very good stats/ml program but it's CMU so my chances are really low there. I think a CS program would fit my interests best but i dont think i have the necessary background. would prefer to stay in the northeast area but that's low on my list of priorities.

 

i feel like i'm capable of handling being in a hard program but i have nothing to prove it..which sucks.

 
so to be specific, my questions are:

1- which programs do you think would fit my interests best: applied math, stats, cs or OR?

2- which programs do you think i have a good shot of getting into? 
3-what do you think i could do to prepare? im intending to apply for fall 2016 so i have some time i think.

Edited December 15, 2013 by mbwh

[Funkoverload]

very impressive spec. how do you think of econ phd? you can still do everything in there (econometrics theory or application or math econ or other applied econ areas and so on...) 

[jdoe192]

im going to be a complete noob here and ask what "spec" is! 
I've been feeling more inclined to get into a stats/cs/or program because i feel like they're more heavy on the methods, which i prefer. 

could you suggest a specific econ program? what i usually do is look at the research interests of the faculty/ student dissertations and see if what they're researching is of interest to me.

thanks a lot!

[DMX]

i'm in a similar boat (interested in ML, but not sure if stat/cs/or is right for me) and here's my take on it.

 

CS: you are gonna have a hard time cracking top CS departments. While publications will certainly add to your application, top CS programs are so competitive that they expect CS-related publications (i have a friend who wanted to transition from physics to CS and had publications in top physics journals. but she was unable to crack top 15 and had to settle for 'lesser' schools (which are still good of course!)).

 

OR/applied math: similar story here. OR is extremely competitive (though not as much as CS), and there aren't many applied math departments doing (serious) machine learning.

 

stat: better chance here. applicant pool is shallower. i think you will have a good shot at a decent number of top 15 places.

 

econ: your best bet. i know econ is certainly competitive, but the acceptance % is deflated by a lot of econ grads who haven't even taken multivariable calculus.

 

as you are probably aware, key to cracking CS/OR departments in relevant publications. if you get some publications in relevant journals/conferences by 2015/16 you may have a good shot.

 

good luckl!