1
$\begingroup$

Good day

I would like to get weekly returns data from daily data , I want to use the Wednesday-to-Wednesday approach – the returns (rt) are computed from the Wednesday closing prices Pt , i.e., rt = ln(Pt/Pt-1). In the cases in which Wednesdays were not active trading days, the closing values from the next date with valid prices from the sequence of the nearest days is used: I'm Stata user as well as an excel user

Any hint will be highly appreciated!! thaks!!

$\endgroup$
5
  • 1
    $\begingroup$ consider the following YouTube video I made on how to change time intervals. You would just have to tweek it a bit to get desired Wednesday to Wednesday dates. youtu.be/SHVN-AyU0jk @ama $\endgroup$
    – Rime
    Feb 8, 2015 at 13:20
  • 1
    $\begingroup$ @Rim thank you Rim, It worked great for one company,my issue is that I have thousand of company and I have to repeat that action a thousand of time!! $\endgroup$
    – Ama
    Feb 9, 2015 at 12:26
  • 1
    $\begingroup$ Oh I see. I do not know Stata but I believe there are methods to do this using R-code for various iterations @Ama $\endgroup$
    – Rime
    Feb 9, 2015 at 20:56
  • 1
    $\begingroup$ Ama, Is your issue getting a data set with all the symbols/history you require? If you are familiar with PQ/PP, I'll work up an Excel solution for you. Let me know. Thanks. Jason, A simple but elegant approach. Thanks. $\endgroup$
    – Nin Sute
    Jun 10, 2016 at 9:45
  • 1
    $\begingroup$ @Nin sute, thank you very much for your help yes sure I would be very grateful if you helped me out with that!! $\endgroup$
    – Ama
    Jun 13, 2016 at 10:40

1 Answer 1

2
$\begingroup$

You can compute daily gross returns and then simply multiply them: $R_w=\prod_i \left(1+R_i \right)-1$, where $R_i=P_{close,i}/P_{close,i-1}-1$

$\endgroup$
1
  • $\begingroup$ If you do some analytics you will figure out that $R_w=P_{close,the-last-day-of-the-week}/P_{close,the-last-day-before-the-week}$ So, there are much less computations $\endgroup$
    – Andrew
    Jun 13, 2016 at 19:37

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

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