1
$\begingroup$

I have 36 months of relative returns and I need to calculate the annualised tracking error.

So, using 36 months of returns is it simply like below:

stdev(36 months of returns) * sqrt(12)

Why the sqrt(12)?

$\endgroup$
1
$\begingroup$

$\sqrt{12}$ annualizes monthly deviations.

But I don't understand why you measure tracking error with stdev. It should be $$ ATE = \sqrt{\frac{12}{36}\sum_{i=1}^{36}(r_{b,i}-r_{t,i})^2}$$ where $r_{b,i}$ is benchmark return for month $i$ and $r_{t,i}$ is tracking portfolio return for same period. So you shouldn't substract average error inside square.

$\endgroup$
  • $\begingroup$ This is correct, in particular, for ETFs. The scaling is needed for annualization. The same treatment is also employed for historical volatility estimation based on daily asset prices. $\endgroup$ – Gordon Nov 2 '15 at 14:42
  • 1
    $\begingroup$ I think his "returns" are as indicated in the question "relative" returns so they correspond to $\bar{r}_i = r_{t,i} - r_{b,i}$, then he uses the approach from wiki $TE=\sqrt{\text{Var}(\bar{r}_i)}$ is that wrong? $\endgroup$ – SRKX Nov 3 '15 at 3:37
  • $\begingroup$ I have also encountered tracking error formulas without the negative average excess return term. Which is it? $\endgroup$ – user1627466 Aug 9 '17 at 6:52
  • $\begingroup$ SRKX, it's Ok but correct to get annualised value. $\endgroup$ – hvedrung Aug 10 '17 at 14:00

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.