Non-parametric test statistics for event studies

[Tony Kwabena]

Dear All,

I was wondering if there is a way to compute the following non-parametric test statistics for daily average abnormal returns in stata? (1) Corrado rank test (2) Corrado and Zivney sign test (3) Generalized sign test (Cowan 1992)

[Steve Samuels]

Welcome to Statalist, Tony! A quick Google search shows repeated questions over the years about the Corrado tests (whatever those are) in Stata, and there has not been a positive answer. About these tests and the "Generalized" test, I refer to the FAQ:

13. Literature references

Please give precise literature references. The literature familiar to you will be not be familiar to all members of Statalist. Do not refer to publications with just author and date, as in Sue, Grabbit, and Runne (1989).

Steve

[Marco Ceccarelli]

Tony is probably refering to the Corrado & Charles (1989) test [Corrado, Charles J. (1989): A nonparametric test for abnormal security-price performance in event studies. In Journal of Financial Economics 23 (2), pp. 385–395.]
The question would interest me as well, especially since I am trying to compute the signs of the abnormal returns (ARs) during my estimation window. The signtest Stata test does go in the good direction, but I can't really use for the comparison within the regression...
Say I have a regression and store the following results:

quietly reg D_`var' D_mkt if date<`endDate' & date>=`startDate'
A_`var' = _b[_cons] if (date+30)==`endDate'
B_`var' = _b[D_mkt] if (date+30)==`endDate'

I need to enumerate the number of observations where the estimated value is larger than the actual value... but it dosen't seem to work.