Date: Tue, 6 Dec 2005 12:21:15 -0600
Reply-To: "Swank, Paul R" <Paul.R.Swank@uth.tmc.edu>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: "Swank, Paul R" <Paul.R.Swank@uth.tmc.edu>
Subject: Re: Significance testing between R-square from linear and
R-square from curvilinear regression (Revised).
Content-Type: text/plain; charset="us-ascii"
Steiger's multicor program will do that.
"Want to compare multiple, partial, or canonical correlations for
Steiger and Browne (1984) show how you can do this by reprasing the
hypothesis as a pattern hypothesis testable by MULTICORR. For a recent
review of some related correlational tests, see Olkin and Finn (1995).
Olkin, I., and Finn, J.D. (1995). Correlations redux. Psychological
Bulletin, 118, 155-164.
Steiger, J.H. (1979). Multicorr: a computer program for fast, accurate,
small-sample tests of correlational pattern hypotheses. Educational and
Psychological Measurement, 39, 677-680.
Steiger, J.H. (1980). Tests for comparing elements of a correlation
matrix. Psychological Bulletin, 87, 245-251.
Steiger, J.H., & Browne, M.W. (1984). The comparison of interdependent
correlations between optimal linear composites. Psychometrika, 49,
Paul R. Swank, Ph.D.
Professor, Developmental Pediatrics
Director of Research, Center for Improving the Readiness of Children for
Learning and Education (C.I.R.C.L.E.)
UT Health Science Center at Houston
From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of
Sent: Tuesday, December 06, 2005 11:18 AM
Subject: Significance testing between R-square from linear and R-square
from curvilinear regression (Revised).
Hi, I want to clarify my question in previous question.
I have two variables, X: time (11 time points) and Y: means of
evaluation (one group, N = 132).
I expect that exponential function will fit better than a linear
function to predict the trajectory.
I did a curve estimation with exponential function and found R-square
from the exponential function is greater than R-square from a linear
But how can I test if the difference in R-squares is signifcant?
I found a formular in Blalock (1972). But it requires correlation
between Y and transformed Y.
Should I do time series analysis?
Any help will be greately appreciated. Thanks in advance,
Sungeun Chung, Ph.D.
Department of Communication
Memorial Hall 303G
Western Illinois University
Macomb, IL 61455-1390
Tel. (309) 298-2219
E-mail: S-Chung@wiu.edu; email@example.com