Month effects on stock returns

[Michael Faraday]

Hello,

I've got a dataset of historical daily stock prices for 20 companies between 1st January 2010- 31st December 2020 on the US stock exchange. i seek to find whether there are any month effects in stock returns (for example, December effects).

Any help ?

[George Ford]

returns or abnormal returns?

[Michael Faraday]

returns

[George Ford]

I suppose you could compute return from first/last day of month, and then just dummy the month. Or, use daily returns regress that on a month dummy (or full set of month dummies). The former is a month effect, while the latter says daily returns tend to be higher/lower in the month. My guess is the results will be comparable (though perhaps of different scale). Probably two-way fixed effects model with company/year fixed effects. With 10, you're at the limit of clustered errors (could use boottest to check). Probably need the market return in the regression.

https://papers.ssrn.com/sol3/papers.cfm?abstract_id=429847
https://www.semanticscholar.org/paper/The-January-Effect%3A-Still-There-after-All-These-Haugen-Jorion/0eab85e09b01b6cadc1d001ef2929094b1d77b9b