Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: A vvvvvery naive question about "controll for"


From   Sean <asmileguo@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: A vvvvvery naive question about "controll for"
Date   Sat, 15 Oct 2005 12:33:44 -0500

Dear Statalist users,

I wish I'm not asking something very naive. Does including a var as an
additional regressor mean this var is being controlled for? In
physical science as far as I understand, "control" means maintaining
some conditions at the same level for all the subjects under
experiment; but in social science this is hardly true, so putting one
variable indicating the difference of one aspect among these subjects
really "controls" this aspect? If this is true, then I come to an
absurd conclusion that physicists should learn from social scientists:
putting more and more variables into one regression instead of
spending lots of funds in building up expensive labotories to
"control" some things.

I doubt so but never figured out a satisfactory answer. Any opinions?


--
Best Regards,

Sean

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index