Let us assume the geometric Brownian motion, and we have $$dS_t= uS_tdt+\sigma S_tdz,$$ and $S_t$ follows a log-normal distribution, but why is $r_t$, the continuously compounded rate of return, normally distributed?

  • $\begingroup$ I edited the question a bit to make it clearer - I hope, I got it right. $\endgroup$ – Ric Apr 7 '15 at 15:02
  • $\begingroup$ @Richard I would rather call it continuously compounded rate of return instead of log return. $\endgroup$ – ZHI Apr 7 '15 at 15:07
  • $\begingroup$ It is absolutely usual to call it log-return as far as I know ... it was simply necessary to say what $r_t$ could mean ... please formulate your question clearly in the future. $\endgroup$ – Ric Apr 8 '15 at 8:02

The solution to the above SDE is (this is will known and can be seen by applying Ito's lemma) $$ S_t = S_0 \exp\left( (u-\sigma^2/2) t + \sigma B_t \right), $$ Thus the log-return is given by $$ \log(S_t/S_0) = (u-\sigma^2/2) t + \sigma B_t $$ and is normally distributed as $B_t$, Brownian motion at time $t$, is normally distributed. In fact the distribution of the expression above is $N( (u-\sigma^2/2) t, t \sigma^2)$. If we assume that $t=1$ (one day or one year) then we get $N( (u-\sigma^2/2),\sigma^2)$ and have the interpretation of the parameters in this frequency.

| improve this answer | |
  • $\begingroup$ +1, perhaps you should add that the log of a log-normally distributed random variable is normally distributed, that log of a division is equal to the difference between the logs of both values and that the difference of two normally distributed random variables is again normally distributed. $\endgroup$ – vonjd Apr 7 '15 at 16:10
  • 1
    $\begingroup$ Your comment gives additional input. One could say so many things ... I will add one more comment.. $\endgroup$ – Ric Apr 8 '15 at 7:06

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.