I think the only way to do this with CA is to ignore gender (husband/wife), and analyse the table of respondent occupation by spouse occupation. The scores for respondent occupation would then be the status scale. Ken At 09:11 AM 29/06/2007, you wrote: >Hello all I am looking at levels of social interaction in New Zealand society >using census data sets using simple correspondence analysis. I am conducting >the CA analysis on a two-dimensional of husband/wife occupations (as is >found in the Camsis scale). I was thinking about whether it was possible to >generate a single set of scores representing the best-fitting >intercorrelation of >these two sets of occupational categories rather than the current two >sets of scores for each dimension. Are you able to point me in the right >direction that may offer some examples or references? >Cheers Stephen > >---------------------------------------------- >CLASS-L list. >Instructions: http://www.classification-society.org/csna/lists.html#class-l ---------------------------------------------- CLASS-L list. Instructions: http://www.classification-society.org/csna/lists.html#class-l