[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Mean Correction

From   "Pavlos C. Symeou" <>
Subject   st: Mean Correction
Date   Tue, 11 Sep 2007 10:36:24 +0100

Dear Statalisters,

In many papers authors appear to mean-correct variables prior to 
estimation for certain reasons. Namely, they divide the respective 
variables by their geometric means. However, in a panel data environment 
this raises the question "Which geometric mean should I use?". Should I 
divide my variables with a Country-specific geometric mean (using 
"bysort country"); should I use Yearly-specific geometric mean (using 
"bysort year"); or a pooled geometric mean for all years and countries?

Thank you.

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index