Statalist


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

Re: st: RE: Linear Regression


From   Steven Samuels <sjhsamuels@earthlink.net>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: RE: Linear Regression
Date   Fri, 8 Aug 2008 10:28:56 -0400

Someone from StataCorp recently noted that it can be done with -nl-

/*******************************************/
sysuse auto
nl (mpg = {b0}+ {b1}*weight + {b2}*weight^2)
/********************************************/

No program with which I am familiar (SAS, R, SPSS, Stata) allows the simpler syntax that Meric would like to use. Either one must create a new variable or create names for all coefficients and supply them to the equation. If Meric is concerned about the effort of adding many polynomial terms, then -orthpoly- would be an easy approach.


-Steve


On Aug 8, 2008, at 9:39 AM, Nick Cox wrote:


I am not clear what your question is precisely.

But if you want to -regress- on something and its square, you need to
-generate- the square as a new variable before you can do it, unless it
exists already.

I am not clear what you mean by "efficient", but I don't think there is
another way to do it.

Nick
n.j.cox@durham.ac.uk

Meric Osman

I have a problem about writing my regression equation. I want to add
the variable and its square at the same time. Such as

y = a + a^2 + ...

Actually, I can do it by generating a new variable which is a*a, but I
don't wanna do that because it is not an efficient way.

*
* 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