From: "Daniel Robbins" <>
Newsgroups: comp.soft-sys.matlab
Subject: Identifying linear vs  curvilinear relationship
Date: Fri, 8 Mar 2013 11:45:07 +0000 (UTC)
Organization: The MathWorks, Inc.
Lines: 11
Message-ID: <khcj02$5id$>
Reply-To: "Daniel Robbins" <>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
X-Trace: 1362743107 5709 (8 Mar 2013 11:45:07 GMT)
NNTP-Posting-Date: Fri, 8 Mar 2013 11:45:07 +0000 (UTC)
X-Newsreader: MATLAB Central Newsreader 2776992
Xref: comp.soft-sys.matlab:790639


Can anyone advise on the best method to identify if the relationship between two varibales is linear or curvilinear? I am collecting data which includes both.

Potentially I could calculate both and then use an 'IF' function to detect the highest R^2 value, but this seems long winded. I am presuming there is a better approach to automate this process.

FYI, I dont have the curvefitting toolbox...

Any thoughts are greatly appreciated!