For details of how SPSS does the t-test, try ...

/Help/Statistics Coach/Compare Groups for Significant Differences/ ... /T Test Algorithms

Art ************************* Art Burke Associate, Evaluation Program Education Northwest 101 SW Main St, Ste 500 Portland, OR 97204 Phone: 503.275.9592 Art.Burke@educationnorthwest.org http://educationnorthwest.org We have recently changed our name to "Education Northwest" from "Northwest Regional Educational Laboratory." Please note the new e-mail and Web addresses in the signature above. You may continue to find us on the Web at http://www.nwrel.org for the immediate future as well. ************************

-----Original Message----- From: Wang Xu [mailto:dachengruoque@163.COM] Sent: Tuesday, October 27, 2009 7:30 PM To: SPSSX-L@LISTSERV.UGA.EDU Subject: how to compute this?

Hi all list members, I am a green hand at data analysis. Recently I was bumped by a scenario presented in a paper by Roger Kirk Kirk, R. E. (1996). Practical Significance: A Concept Whose Time Has Come. Educational and Psychological Measurement, 56(5), 746-759. on the page 755 of the paper the 2nd paragraph there is it. The summary of the scenario is as follows, 13 patients were assigned evenly to control and experimental groups.t(10) =1.61, p=.14, the mean for experimetal group is 13 IQ points higher than that of control group. At the end of the paragraph the author said that a 95% confidence interval for the population mean difference is likely to be between -6.3 and 32.3 IQ points. Do all the present conditions necessiate the computation of confidence interval for the population mean difference? I thought that there should be one more condition: standard deviation. Am I right? In spss there is always some computation of confidence interval for the population mean difference? How is it computed ? What is the formla for computing this? Thanks a lot!

W.X.

===================== To manage your subscription to SPSSX-L, send a message to LISTSERV@LISTSERV.UGA.EDU (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

===================== To manage your subscription to SPSSX-L, send a message to LISTSERV@LISTSERV.UGA.EDU (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD