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

RE: st: RE: Simulation question (now: equation solving problem)


From   "FEIVESON, ALAN H. (AL) (JSC-SK) (NASA)" <[email protected]>
To   "'[email protected]'" <[email protected]>
Subject   RE: st: RE: Simulation question (now: equation solving problem)
Date   Thu, 3 Feb 2005 16:08:02 -0600

Amadou - 


How about:

gen d=2
reg d X Y Z, nocons

Obviously, you can't solve the equation exactly - you will get a
least-squares solution.

Al F.

-----Original Message-----
From: [email protected]
[mailto:[email protected]]On Behalf Of
[email protected]
Sent: Thursday, February 03, 2005 1:53 PM
To: [email protected]
Subject: RE: st: RE: Simulation question (now: equation solving problem)


Dear all,

Your're right. It's a matter of convention.
I've been thought in school of "independent" and "dependent" variables.
As long as I know what is what, it is not a big issue to me.

Coming back to my initial problem, I think I want to solve something like:

aX + bY + cZ = d

where a, b, c are coefficients issues from the regression (my "betas" if I
can
say so) and X, Y, Z are vectors of observations (in my case POP and INVEST).

d is equal to 2, if I stick to my previous problem of doubling my GDP.

Is there a way to solve such an equation in stata?

Best regards.

Amadou.




 

                      "FEIVESON, ALAN H. (AL)

                      (JSC-SK) (NASA)"                 To:
"'[email protected]'" <[email protected]>       
                      <[email protected]        cc:

                      >                                Subject:  RE: st: RE:
Simulation question                                           
                      Sent by:

                      owner-statalist@hsphsun2.

                      harvard.edu

 

 

                      02/03/2005 01:44 PM

                      Please respond to

                      statalist

 

 

 

 





One convention that I like, is that if a variable is set by design in a
prospective study, it is "independent". If a variable is observed and is the
measure upon which one desires to do statistical inference, it is a
"dependent variable". If is observed or measured in conjuntion with the
dependent variable, but is not a "dependent" variable it is a "covariate".

Al Feiveson

-----Original Message-----
From: [email protected]
[mailto:[email protected]]On Behalf Of David Kantor
Sent: Thursday, February 03, 2005 11:05 AM
To: [email protected]
Subject: RE: st: RE: Simulation question


I, too, like terminology such as response/predictor/covariate.  But we
usually use "outcome" in place of "response".

Then we often analyze family economic data, and we find ourselves in the
paradoxical situation where our outcome is income.

-- David


At 08:46 AM 2/3/2005 -0800, John Wallace wrote:
>I too prefer the response/predictor/covariate terminology.  Sometimes
>someone will ask if "response" means "independent" - that's as much
>conflict as I've ever encountered over it.  I like terms that sort of
>have their definitions built into them.
>[...]

David Kantor
Institute for Policy Studies
Johns Hopkins University
[email protected]
410-516-5404
*
*   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/
*
*   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/




*
*   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/
*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index