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 (February 2005)Back to main SPSSX-L pageJoin or leave SPSSX-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Wed, 23 Feb 2005 14:39:25 +0100
Reply-To:     Rouckhout Danny <Danny.Rouckhout@lessius-ho.be>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Rouckhout Danny <Danny.Rouckhout@lessius-ho.be>
Subject:      effect size and non normal distribution
Content-Type: text/plain; charset="iso-8859-1"

Hi all, We recently compared the testscores from two samples (clinical versus non-clinical). Both samples show a very strong deviation from a normal distribution (as was expected with psychopatological characteristics). In addition with the common significance we wanted to calculate the effect size and the confidence interval for the effect size. However, effect size calculations are based on the assumption of a normal distribution. How can we determine a more appropriate effect size and CI. Are there any SPSS syntax files for this problem?

I read a recent article about the problem [Kelley, K.(2005) The effects of nonnormal distributions on confidence intervals around the standardized mean difference: bootstrap and parametric confidence intervals, Educational and Psychological Measurement, ol 65, 1, p51-69] that included a syntax for another statistical package. However, my syntax an math knowledge was inadequate to put it in an SPSS syntax.

Are there any suggestions?

Danny Rouckhout University Hospital Antwerp Dept Psychiatrie Wilrijkstraat 10 2650 Edegem Belgium


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