I don't know if there is a convention, but 1 standard error has always made sense to me. If the error bars for two groups do not overlap, you can be reasonably confident (but not certain) that the means are significantly different.
************************************************* Michael T. Scoles, Ph.D. Director, Arkansas Charter School Resource Center Associate Professor of Psychology & Counseling University of Central Arkansas Conway, AR 72035 voice: (501) 450-5418 fax: (501) 450-5424 ************************************************* > -----Original Message----- > From: Robert Herdegen [mailto:[EMAIL PROTECTED] > Sent: Tuesday, March 23, 2004 2:12 PM > To: Teaching in the Psychological Sciences > Subject: Graph Question: Error Bars > > > TIPSters: > > I'm working with a student on preparing graphs for his > senior thesis. He > plans to include error bars with each of the points on his > figures, but I'm > not sure whether there is a convention for *what* is to be > displayed in > error bars: standard deviation? standard error? confidence > intervals? The > values are all different, of course, and each shows > something a little > different. Are there any standards for what one should show > in error bars? > > Bob Herdegen > > ******************************************** > Robert T. Herdegen III > Elliott Professor of Psychology and Chairman > Department of Psychology > Hampden-Sydney College > Hampden-Sydney, VA 23943 > 434-223-6166 > [EMAIL PROTECTED] > ******************************************** > > > --- > You are currently subscribed to tips as: [EMAIL PROTECTED] > To unsubscribe send a blank email to > [EMAIL PROTECTED] --- You are currently subscribed to tips as: [EMAIL PROTECTED] To unsubscribe send a blank email to [EMAIL PROTECTED]
