This is a multi-part message in MIME format.
------=_NextPart_000_00C8_01BF5524.4BF9A9E0
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
> . . .But how to measure, non-linear relation for 2 continuous =
variables.=20
>=20
> Thanks
If you do an x-y plot of your data in Excel, you can choose to add a =
regression line, and try the fit of linear, exponential, polynomial, =
etc. models The output includes a value of R^2 for the chosen fit to =
help you evaluate it. So clearly Excel thinks it is possible to compute =
a correlation for the nonlinear cases. Sorry, I do not know the formula =
used by Excel to do this.
------=_NextPart_000_00C8_01BF5524.4BF9A9E0
Content-Type: text/html;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META content=3D"text/html; charset=3Diso-8859-1" =
http-equiv=3DContent-Type>
<META content=3D"MSHTML 5.00.2614.3500" name=3DGENERATOR>
<STYLE></STYLE>
</HEAD>
<BODY bgColor=3D#ffffff>
<DIV><FONT size=3D2>
<DIV>> . . .But how to measure, non-linear relation for 2 continuous=20
variables. <BR>> <BR>> Thanks</DIV>
<DIV> </DIV>
<DIV>If you do an x-y plot of your data in Excel, you can choose to =
add a=20
regression line, and try the fit of linear, exponential, =
polynomial, etc.=20
models The output includes a value of R^2 for the chosen fit =
to help=20
you evaluate it. So clearly Excel thinks it is possible to compute =
a=20
correlation for the nonlinear cases. Sorry, I do not know the =
formula used=20
by Excel to do this.</DIV></FONT></DIV></BODY></HTML>
------=_NextPart_000_00C8_01BF5524.4BF9A9E0--
