• C++ Programming for Financial Engineering
    Highly recommended by thousands of MFE students. Covers essential C++ topics with applications to financial engineering. Learn more Join!
    Python for Finance with Intro to Data Science
    Gain practical understanding of Python to read, understand, and write professional Python code for your first day on the job. Learn more Join!
    An Intuition-Based Options Primer for FE
    Ideal for entry level positions interviews and graduate studies, specializing in options trading arbitrage and options valuation models. Learn more Join!

Time Series or Stochastics

Joined
7/5/18
Messages
70
Points
28
I have an elective opening for my final semester, MS Statistics, and I have gotten the approval to do it online, so long it is from an accredited school. I was originally leaning towards times series because my school doesn't have a dedicated class (Its bio-statistics focused). But since I have free reign, stochastic calculus is another option.

Lofty goal is to get into quantitative trading, real-world goal is more of desk, risk, or research quant. So the pragmatist in me is asking, which one is more marketable and/or useful in starting a career.
 
I would second time series as well. I feel it has a lot of applicable applications which could be beneficial for your job search as well.
 
I'd vouch for times series any time, the reason being it has grown and it's more mature to capture some aspect which can't be fitted in stochastic realm. For example, the features time series will captures has been over simplified by stochastic in a way that seem to good to evaluate particular scenarios
 
I'm not sure about your background and your goals. I can only give some general opinions. Time series traditionally belongs to statistics field, and departments of economics also offer courses for TS under the concepts of econometrics. However, I feel the statistics concepts in TS are actually straight forward, on the contrary, mathematics are more complicated in TS compared with other statistics field.

It looks to me, Texas A&M covers major concepts(trend, seasonality, stationarity) of TS and application in R. Beside those major points, Penn State also extends the contents to multivariate TS. NC State course requires more mathematics, it covers both time domain and frequency domain methods. I've noticed they mention they may cover some advanced topics such as long memory, conditional heteroscedasticity if time permits.
 
I'm not sure about your background and your goals. I can only give some general opinions. Time series traditionally belongs to statistics field, and departments of economics also offer courses for TS under the concepts of econometrics. However, I feel the statistics concepts in TS are actually straight forward, on the contrary, mathematics are more complicated in TS compared with other statistics field.
Well said. The backcasting operator threw me for a loop. The frequency domain stuff is also pretty far out if you haven’t seen it before.
 
Both of them are great, but I would emphasize more on time series because of its wider application.
 
btw: When I started to learn backcasting operator, I always mistook it for a variable.
At first, I used to think that S_t == dS/dt (Mathematicians use S(t)).
LOL
I can't be blamed because the prof didn't define it.
 
Back
Top