SPSS Conjoint Analysis question

[gopalaganesh]

Hi:

I have attached the Overall Statistics page from an Ortho Plan run.

My question has to do with the very last table on the attached page. How are (i.e. the procedure) the overall R, Tau, holdout Tau and their three values calculated? I have verified that everything else on the page is a simple average of values for the the 100+ cases in my output. However, when I tried averaging the above stats, those results are far, far removed from the overall R, Tau and holdout Tau. I wonder whether the above overall statistics are the result of running correlations among the 100 individual R's, Tau's and holdout Tau's.  Thanks, - gg

[gopalaganesh]

sorry, the attachment got left out, let me try again! - ggOverallStatistics.pdf

[Rick Oliver-3]

You might find the answer here:

ftp://public.dhe.ibm.com/software/analytics/spss/documentation/statistics/24.0/en/client/Manuals/IBM_SPSS_Statistics_Algorithms.pdf




Rick Oliver
Senior Information Developer
IBM Business Analytics (SPSS)
E-mail: [hidden email]



From:        gopalaganesh <[hidden email]>
To:        [hidden email]
Date:        07/20/2016 04:07 PM
Subject:        SPSS Conjoint Analysis question
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

Hi:

I have attached the Overall Statistics page from an Ortho Plan run.

My question has to do with the very last table on the attached page. How are
(i.e. the procedure) the overall R, Tau, holdout Tau and their three values
calculated? I have verified that everything else on the page is a simple
average of values for the the 100+ cases in my output. However, when I tried
averaging the above stats, those results are far, far removed from the
overall R, Tau and holdout Tau. I wonder whether the above overall
statistics are the result of running correlations among the 100 individual
R's, Tau's and holdout Tau's.  Thanks, - gg



--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/SPSS-Conjoint-Analysis-question-tp5732796.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (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 [hidden email] (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