Hi all,
I am new to Stata and I have the following problem.
I have to conduct an event study for 1,500 US firms, having different event dates, i.e. announcement of activism campaign.
I have the following data:
- For each firm, I have the series of returns in the 250 days before the announcement, paired (in the next column) with the corresponding date
- For each of the 4 Fama French Carhart factors, I have the series of returns paired with the corresponding dates, which cover the entire of range of dates of the returns of the firms.
As far as I am concerned, the first step would be to estimate a time series regression of the returns of a firm on the returns 4 Fama-French-Carhart factors in the 250 days before the announcement. This time series regression should be repeated for each firm in the sample, so:
- The y variable (i.e. returns of the firm) should be different in each of the 1,500 time series regressions;
- The dependent variables are the same for each regression (FFC factors)
- The 250 dates are different for each regression
I was thinking to build a "loop" that for each company should automatically regress its returns on the 4 FFC Factors, automatically selecting only 250 the relevant dates for the FFC factors.
Did I explain sufficiently clearly my problem?
Any suggestions on how to do it?
Related Posts with Loop of time series regression
annual cross sectional regression versus panel regressionDear all In one article I have read that they estimate "average coefficients from ten annual (2005–2…
cmset choice models in Stata 16I am trying to figure out the new choice model (cmset) analysis for results of the discrete choice e…
New to stata need help.hi my final year project involves analyzing bicycle crashes in my state, im new to the software stat…
Multiple tabulate for different yearsHello, I am trying to put together a table to see the frequency of occurrence of 1 (it is a dummy v…
Industry Adjusted Measurehello, Please guide me about this comment. I am using agency cost measure as dependent variable (sel…
Subscribe to:
Post Comments (Atom)
0 Response to Loop of time series regression
Post a Comment