Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: can I get standardized coefficients by standardize variables first?


From   "Martin Weiss" <martin.weiss1@gmx.de>
To   <statalist@hsphsun2.harvard.edu>
Subject   Re: st: can I get standardized coefficients by standardize variables first?
Date   Tue, 3 Mar 2009 21:24:55 +0100

<>
"What's stopping you from doing what you need you to do in a spreadsheet package?"

Could you explain what your advice is for Mandy? What could a spreadsheet add to the solution for her problem?


HTH
Martin
_______________________
----- Original Message ----- From: "Clive Nicholas" <clivelists@googlemail.com>
To: <statalist@hsphsun2.harvard.edu>
Sent: Tuesday, March 03, 2009 9:19 PM
Subject: Re: st: can I get standardized coefficients by standardize variables first?


Mandy Fu:

I'm running some panal data. So the commands I 'll use are something
like -xtreg , fe-, or -xtreg,re-. Since the beta coeffients
(standardized coefficients) are not an option for xtreg command, I
tried to standardize all the variables in the whole data set first
and then use the panel data methods on the standardized variables:
-------------
.local var y x1 x2 x3 x4
.egen new_`var'=std(`var')
.xtreg `var',fe
---------------
But the results are different from using the beta coefficients got
from an OLS regression adding dummy variables to indicate the group
variable i for the panel data.
-----------------------------------------
**dummy1,dummy2,..dummyn are the dummy vriables based on group i.
.reg y x1 x2 x3 x4 dummy*,b
-----------------------------------------
Could someone give me some hints why the results from these two ways
are different? Is it a correct way to get beta coefficents by
standardized variables first and then use the regular commands?

What's stopping you from doing what you need you to do in a spreadsheet package?

--
Clive Nicholas

[Please DO NOT mail me personally here, but at
<clivenicholas@hotmail.com>. Please respond to contributions I make in
a list thread here. Thanks!]

"My colleagues in the social sciences talk a great deal about
methodology. I prefer to call it style." -- Freeman J. Dyson.

*
*   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/



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