RE: st: Wilcoxon symmetry

[Denis Haine <denis_haine@hotmail.com>]

Hello Simone,

Maybe you could check Johnson's corrected t-test (see help johnson and Stata Technical Bulletin STB-26 (sg40).

Denis


> Date: Sat, 6 Mar 2010 20:36:07 +0100
> From: simonespleis@gmx.de
> Subject: st: Wilcoxon symmetry
> To: statalist@hsphsun2.harvard.edu
> 
> Dear all,
> 
> I am implementing an event study and testing absolute(!) abnormal returns since I cannot classify the news (positive or negative). Now I am trying to find a cross-sectional test for detecting abnormal returns on the event date. In a paper I read that the author implemented the Wilcoxon-signed-rank-test for the event date. But this test assumes a symmetric distribution, or am I mistaken? Since absolute abnormal returns will not be symmetric (something close to a half-normal-distribution) I am therefore looking for a test that does the trick to avoid the symmetry assumption and still detects abnormal performance.
> 
> I would greatly appreciate a hint!
> 
> Best regards,
> 
> Simone
> -- 
> Sicherer, schneller und einfacher. Die aktuellen Internet-Browser -
> jetzt kostenlos herunterladen! http://portal.gmx.net/de/go/chbrowser
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
 		 	   		  
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/