Event study

**Maximilian W** · 11-10-2017, 04:26 PM

Hi all,

I am conducting an event study using Excel, analyzing how social media posts are affecting stock prices. Is it statistically allowed to have a different number of observations per event window?

E.g. to have in event window [0;1] 120 observations for which the abnormal returns are analyzed with the t-test; while having in event window [0;3] only 60 observations?

I controlled for confounding events - per respective event window. E.g. when earnings where released in t=2 I still used the observation in event window [0;1] but not in [0;3].

I wondering if its correct to then conclude e.g. that abnormal returns in [0;1] are significant, but not in [0;3].

Thank you so much!!!

PS: I followed McWilliams &Siegel (1997, S. 647) approach with the confounding events - but begin to think I did it wrong, because every other event study uses the same number of observations per event window...

**Kaper** · 11-11-2017, 03:14 AM

Will you please attach a SMALL sample Excel workbook(s) (10-20 rows of data is usually enough)? Please don't attach a picture of one (no-one will want to re-type all your stuff before starting).

1. Make sure that your sample data are truly REPRESENTATIVE of your real data. (If trere are typical cases like: all unique values/duplicates could occur, day/night, nobody present/several persons at once, before/on/past due, etc. - please show them all or at least indicate in text) The use of unrepresentative data is very frustrating and can lead to long delays in reaching a solution.

2. Make sure that your desired solution(s) is/are also shown (mock up the results manually).

3. Make sure that all confidential/restricted information (either personal or business) like real e-mails, social security numbers, bank accounts, etc. is removed first!!

To attach an Excel file you have to do the following: Just before posting, scroll down and press Go Advanced button and then scroll down and press Manage Attachments link. Now follow the instructions at the top of that pop-up screen.

**Maximilian W** · 11-11-2017, 04:49 AM

Hi Kaper,

thanks for your reply!

I attached my Excel file with my solutions and an example of how I calculated t-Value and z-Value.

I think its more about, if its allowed to derive a conclusion like "cumulative average abnormal return from day 0-1 is insignificant, and from 0-3 it is significant" - even though the sample (size) is varying between time horizons.

Thank you!