Jillian wrote:
>In doing regression analysis, is it possible for the output to show the
partial R-squares to determine how much
>each variable contributes to the explained variance?
You can use -pcorr2- command to get a table of coefficients of partial
determination:
. net describe pcorr2, from(http://fmwww.bc.edu/RePEc/bocode/p)
Example:
. sysuse auto, clear
. pcorr2 mpg weight length
--------------------------------------------------------------------------
. sysuse auto, clear
(1978 Automobile Data)
. pcorr2 mpg weight length
(obs=74)
Partial and Semipartial correlations of mpg with
Variable | Partial SemiP Partial^2 SemiP^2 Sig.
-------------+------------------------------------------------------------
weight | -0.2769 -0.1677 0.0767 0.0281 0.018
length | -0.1682 -0.0993 0.0283 0.0099 0.155
--Yulia
[email protected]
*
* 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/
