Help in using Correspondence Analysis

[ksinghravi]

Hi,
I have 1000 observations for 6 different products. Each product is rated on a scale of 1 to 10 on 12 attributes. I want to have a perceptual map for each product with respect to attributes. The problem is I think correspondence analysis can only be used with frequency data, and not with this type of data. If we can transform this scale some how...

Thanks... Your suggestions are welcome

[Jignesh Sutar]

You could transform the 10 point scale to one of dichotomous nature by taking top box scores, those scoring 8 and above, for example. And so then take the frequency count of the top box scores as inputs for your correspondence maps.

On 6 May 2015 at 15:03, ksinghravi <[hidden email]> wrote:

Hi,
I have 1000 observations for 6 different products. Each product is rated on
a scale of 1 to 10 on 12 attributes. I want to have a perceptual map for
each product with respect to attributes. The problem is I think
correspondence analysis can only be used with frequency data, and not with
this type of data. If we can transform this scale some how...

Thanks... Your suggestions are welcome



--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Help-in-using-Correspondence-Analysis-tp5729501.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