I have time series data for a total of 4 stocks and want to analyze the volatility of those. Moreover I want to demonstrate that they have the same volatility. As a response variable I would use log returns, but I simply don't understand which model I should use. Can anyone help? Is there maybe a simple way suited for undergrads? Thank you.

  • 1
    $\begingroup$ You are basically testing whether the log-returns have equal variance or not. There are a variety of statistical tests for this, the simplest is the F-test for equal variances en.wikipedia.org/wiki/F-test_of_equality_of_variances $\endgroup$ – Alex C Jun 22 '18 at 15:46
  • 2
    $\begingroup$ @AlexC, an F-test would require the log-returns to be independent over time, and that is quite restrictive. $\endgroup$ – Richard Hardy Jun 22 '18 at 16:33
  • $\begingroup$ The Brown Forsythe Test seems more robust, could this be a suitable approach? According to Glass/Hopkins the BF Test is flawed, because we don't know how it handles significant differences in variances, but since I am expecting the variances to be equal the test should work properly, right? $\endgroup$ – user34031 Jun 25 '18 at 8:11

Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Browse other questions tagged or ask your own question.