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 (August 2003)Back to main SPSSX-L pageJoin or leave SPSSX-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Tue, 12 Aug 2003 07:10:16 -0500
Reply-To:     Anthony Babinec <tbabinec@ameritech.net>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Anthony Babinec <tbabinec@ameritech.net>
Subject:      Re: Logistic Regression Chi Square to Effect Size?
Comments: To: "David M. Fresco" <fresco@cattell.psych.upenn.edu>
In-Reply-To:  <p06001a03bb5d5871e4c5@[131.123.236.181]>
Content-Type: text/plain; charset="us-ascii"

David - Presumably, the 95%CI bounds refer to the estimated parameter. To aid interpretation, the regression coefficients from Logistic regression are often exponentiated. It is unclear from what is reported whether the 95%CI values are in the metric of b or exp(b). If you can resolve that, then consider the scale and range of the predictor in question. For example, if the predictor in question is Age, and the coefficient in question is exp(b)=1.1, then a difference of, say, 10 years on the predictor in question translates into an odds shift of 1.1^10 = 2.6. That gives an indication of effect size.

Anthony Babinec

-----Original Message----- From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of David M. Fresco Sent: Monday, August 11, 2003 9:28 AM To: SPSSX-L@LISTSERV.UGA.EDU Subject: Logistic Regression Chi Square to Effect Size?

Dear SSPS List members,

I am reading a journal article and am trying to decipher its findings. The authors have a sample of 312 who either responded or did not respond to a treatment. Using logistic regression with response status as the DV, the authors have two continuous predictors of outcome. The first one is a covariate and the second IV is of interest. Here is how the authors describe their findings for the second predictor: p=0.0413; chi-square=6.391; Coef/SE=2.041; 95%C.I.=1.021-1.176.

I would appreciate some help interpreting this statistically significant finding in terms of an effect size. Thanks in advance. Please cc any replies to my email as I take the digest.

-- David M. Fresco, Ph.D. fresco@kent.edu Department of Psychology Voice: (330) 672-4049 Kent State University Fax: (330) 672-3786 315-A Kent Hall P.O. Box 5190 http://dept.kent.edu/psychology/ Kent, OH 44242-0001 http://www.personal.kent.edu/~dfresco/

ListOwner of Helplessness http://psych.upenn.edu/~fresco/helplessness.html Listowner of Mindfulness http://listserv.kent.edu/archives/mindfulness.html


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