Need advice (current graduate student)

[eternalmorning]

I am a graduate student in biostatistics currently on a leave of absence. My research interest lies in applied (or computational) fields of statistics. I am also interested in Big Data, even though I do not clearly understand what it *actually* means and how it is different from current statistical methodologies. Since I haven't decided my dissertation field yet, I am thinking of making my mathematical and computational background solid. The followings are what I have been doing these days:

 

-self-studying measure theoretic probability

-learning C (I know R and Python already but want to add one more)

-watching European soccer

 

I need some advice on the effectiveness of doing those. I am not sure if it is superior to reading current papers in the fields I am interested in. I don't think I am doing completely silly things, but I would like to know if learning the lower-level programming language or theoretical probability would be beneficial considering that I am leaned to the applied fields. Any advice or recommendation will be appreciated. Thanks!

[Ranger]

Go to courseera.com and sign up (free) for machine learning, neural networks, data science related courses. There are a lot to choose from. Although the intent of these courses is not to train you for graduate level research, it would still serve as a good start. Look at Stanford opencourseware (OCW) as well. CMU CS dept's website has some courses up as well (these are MS-PhD grad level courses).

 

Python may actually be good enough but learning more things can never be discouraged. (Yes it's all helpful! lol)

 

Then pick up Elements of Statistical Learning (by hastie et al) and work your butt off. Knowing theoretical probability (measure theoretic) may or may not be required, but a course on convex optimization maybe useful.

 

After all this you ready to do whatever you want to do (maybe)!

Edited February 19, 2015 by Ranger