Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
up vote 0 down vote favorite

I have 500 rows and three columns. Two of the variables (that i want to analyze) are in ordinal form and the other in scale. However, when i run the correspondence analysis wizard in SPSS i can only select the scale variable and not the ordinals. How is it possible to perform correspondence analysis on the ordinal variables?

I have something like this:

Variable1 | Variable2

..Home . .| Strong

..Work . . | Strong

share|improve this question
2  
I don't face trouble you tell about. Correspondence analysis (both simple and multiple) treats all variables as nominal, whatever level of measure you had explicitly defined for them. – ttnphns Mar 31 '12 at 5:27
i select analyze->Dimension Reduction-> Correspondence Analysis. Only scale variables can be added to row and column. Is there a plugin or something? – JustCurious Mar 31 '12 at 9:01
I could not confirm your finding on SPSS 15, 17, 20. I was able to pull any level variable to the "row" and "column" fields without problem. Anyway, let your variables be scale. As I've said, CA internally treats all variables as nominal. – ttnphns Mar 31 '12 at 13:31
I am working with SPSS 20. If i set variable type to numeric, all the values are discarded. – JustCurious Mar 31 '12 at 16:06
I tried to change the type to scale and run the wizard again. I get the following error :Text: myVariable Command: CORRESPONDENCE A string variable was used in a variable list where only numeric variables are allowed. Execution of this command stops. – JustCurious Mar 31 '12 at 17:03
show 1 more comment

Know someone who can answer? Share a link to this question via email, Google+, Twitter, or Facebook.

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.