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 (September 1998)Back to main SPSSX-L pageJoin or leave SPSSX-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Wed, 30 Sep 1998 14:06:32 -0500
Reply-To:     "Dr. Larry Grimm" <lgrimm@UIC.EDU>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@UGA.CC.UGA.EDU>
From:         "Dr. Larry Grimm" <lgrimm@UIC.EDU>
Subject:      Re: p = .051
Comments: To: Stephen Salbod <ssalbod@FSMAIL.PACE.EDU>
Content-Type: text/plain; charset="us-ascii"

Steve, As Jacob Cohen said, "surely God loves the .06 level as much as the .05 level." There is a voluminous literature on the issue, which amounts to complaining about slavishly adhering to p values as the be all and end all. What you can do is refer to the .06 (and other close values) as marginally significant. HOWEVER, the focus should be on the effect size! A nontrivial effect size that accompanies a p value of .06 is much better than a trivial effect size with a p = .000001. Confidence intervals are also recommended but are currently not used as often as effect size indices. Hope this helps. Larry

At 01:38 PM 9/30/1998 -0400, you wrote: > I am looking for a reference. > > On numerous occasions I have gotten p value between .05 and .06. I have >religiously accepted the null under these circumstances. I was wondering if >there was any literature around addressing the issue of the .051 finding. > > Any references that you can suggest can be sent directly to me. > TIA. Steve >


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