LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous messageNext messagePrevious in topicNext in topicPrevious by same authorNext by same authorPrevious page (April 1998)Back to main SPSSX-L pageJoin or leave SPSSX-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Mon, 13 Apr 1998 17:00:46 +0300
Reply-To:     Amir Hetsroni <amir_h@BARLEY.CTEH.AC.IL>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@UGA.CC.UGA.EDU>
From:         Amir Hetsroni <amir_h@BARLEY.CTEH.AC.IL>
Organization: The Hebrew University of Jerusalem
Subject:      problem with nonlinear regression
Comments: To: "Nichols, David" <nichols@SPSS.COM>
Content-Type: multipart/alternative;

I am working on a database that investigates complex relationship between interest in an object and the inclination to participate in activities in favor of the object.

Based on the "principal components of attitude" theory by Guttman I expected to find a W shape relationship between the interest component and the activities component. It appears that at least as far as it concerns the object of national history - mission accomplished (see the control chart below).

However, when it comes to calculating a regression function I am having a problem. Clearly, the most accurate function is not linear, looks more like to parabolas, but how do I write this function? What value should the parameter(s?) have? I tried to draw a scatter plot to learn more about the function but it appears that when the sample is large even fairly large linear relationship (r>0.6), not to mention this case, look messy on a scatter plot. Can someone give a hand with the estimation of the function or at least hint?

thanks, Amir


The Department of Communication The Hebrew University of Jerusalem

E-Mail: [Image]


Back to: Top of message | Previous page | Main SPSSX-L page