```Date: Thu, 31 Jan 2008 18:30:56 +0100 Reply-To: Marta García-Granero Sender: "SPSSX(r) Discussion" From: Marta García-Granero Subject: Re: Means, averages In-Reply-To: <200801311027.m0VARvNO012670@linhost2.utic.net.ba> Content-Type: text/plain; charset=ISO-8859-2; format=flowed Hi Samir Use ONEWAY with a linear contrast: DATA LIST LIST/Q G (2 F8). BEGIN DATA 1 1 3 1 5 1 3 1 3 1 1 2 3 2 4 2 5 2 4 2 5 3 1 3 4 3 4 3 5 4 4 4 2 4 2 4 2 4 END DATA. ONEWAY Q BY G /CONTRAST= -3 1 1 1 /STATISTICS DESCRIPTIVES. This will gice you the correct significance test for the comparison of group #1 vs average of the other 3. This approach has also the advantage that you can compare 1st group against a weighted average of the other 3 (provided you have a set of weights to quantify the relative contribution of each group to the overall mean). HTH, Marta García-Granero > Hi to all, > > > > I have question about average values. I have data that looks like this: > > > > These are answers on scale from 1-agree to 5-disagree to certain question. Variables V1, V2, V3, V4 > are basically different groups of respondents but all answers are to the same question. It is the > same as this one: > > > > Q G > 1 1 > 3 1 > 5 1 > 3 1 > 3 1 > 1 2 > 3 2 > 4 2 > 5 2 > 4 2 > 5 3 > 1 3 > 4 3 > 4 3 > 5 4 > 4 4 > 2 4 > 2 4 > 2 4 > > Q stands for question and G stands for Group. > > > so now I need to compare means in following way: Group1 vs. average of all other groups. How should > I calculate the average of all other groups? Is it simple as making them all Group2 or should I pay > attention to some other details? > > > > Hope I wrote it clear enough:) > ===================== 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 ```

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