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 1999)Back to main SPSSX-L pageJoin or leave SPSSX-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:         Thu, 19 Aug 1999 12:37:53 -0700
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Dale Glaser <glaser@PACIFIC-SCIENCE.COM>
Subject:      Re: SPSS: t-test: two independent sample
Comments: To: Shail Dobson <dobson_shail@HOTMAIL.COM>
In-Reply-To:  <>
Content-Type: text/plain; charset="iso-8859-1"

Assuming you mean n = 100 per group, the answer, in my opinion, is yes; even though I have seen some intro. texts divide hypothesis testing for two groups as follows: (1) if n is small (e.g., n < 30) and the population standard deviation is unknown then use the t distribution; (2) if n is large and the population standard deviation is known then use z distribution; however, a cursory glance at the research journals will find many examples of t-tests being employed when n is well over 30 per group; further as df increases for the t-distribution, it approximates the z-distribution (i.e., critical value for df > 120 = 1.96, when alpha = .05 for two-tailed test); however, I will be interested if other researchers differ in their opinions...............dale glaser

-----Original Message----- From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of Shail Dobson Sent: Thursday, August 19, 1999 12:02 PM To: SPSSX-L@LISTSERV.UGA.EDU Subject: SPSS: t-test: two independent sample

Can independent t-test for means of two independent samples be performed for sample size over 100? If not, is there any other equivalent test available?

Thank you very much,


______________________________________________________ Get Your Private, Free Email at

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