Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I am currently working on a time series data and I would like to quantify how volatile it is.

Here volatile I mean how "shaky" the series is.

If the series is smooth than it is not volatile.

I have an idea to solve this problem, but it is kind of inconvenient.

The idea is to first do a regression/smoothing on the series. Then compute the sum of squared error between the smoothed series and the original series.

Any other better idea or and references suggest me to have a look?

share|cite|improve this question
How will you do the regression/smoothing. If you use a polynomial of arbitrarily high degree, you can get a smooth curve which is exactly as "volatile" as your time-series. – utdiscant Jul 25 '12 at 5:35
The over fitting/training is also a problem. I am thinking to use spline but I still need to read more about it. – Rein Jul 25 '12 at 6:23
BTW: volatility in finance is more or less standard deviation. – user2468 Jul 25 '12 at 6:26

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.