Hi, I am using correspondence analysis to examine degrees of homogamy/social distance in society using the occupations of husbands and wives as markers of social position. I have done this over five historical points using New Zealand census data (19812001). I'm using the dimension scores (1 and 2) of the CA process to achieve a ranked scale of homogamy/social interaction . It is expected that the order of the ranking will be similar to that of the ranking of occupations in the issco model . This indeed is the case with three of the time periods. At two points in time however this ranking is inverted. Has anyone got tips on how to explain this/switch this around? I believe that the 'best fit model' in correspondence analysis can be a little nebulous. Greenacre talks about 'rotating the axis.' Will this work and how might I do this in SAS?
Any help will be useful.
Cheers, Stephen
________________________________
From: Classification, clustering, and phylogeny estimation [mailto:[log in to unmask]] On Behalf Of Liza Rovniak
Sent: Thursday, 4 September 2008 10:40 a.m.
To: [log in to unmask]
Subject: cluster analysis validation technique
Hi,
I am hoping someone here can help me with a "how to" question on running McIntyre and Blashfield's (1980) nearestcentroid evaluation procedure to validate the stability of my cluster analysis solution. I am a newbie to cluster analysis, so this is my first time running this procedure.
I have a sample of about 900 observations and have randomly split the sample in two (Sample A and Sample B). I conducted hierarchical cluster analysis and then calculated the centroid vectors for a 3cluster solution on each of these two subsamples (i.e., steps 1 through 4 of McIntrye and Blashfield's evaluation technique).
Step 5 of McIntrye and Blashfield's technique is to calculate "the squared Euclidean distance for each of Sample B's objects from each of the centroids of Sample A," and Step 6 is to assign "each object in Sample B to the closest centroid vector." At this point, I am not sure what buttons to press in SPSS to complete the analysis. One possibility I tried is to use Kmeans cluster analysis to achieve these two steps, but Kmeans uses simple Euclidean distance (not squared Euclidean distance as recommended by McIntyre and Blashfield) to assign the observations to clusters. Is this okay? (someone told me it was, but I just want to doublecheck). I would greatly appreciate any guidance on what buttons to press in SPSS/appropriate syntax to complete steps 5 and 6 of this analysis.
Thank you.
Liza Rovniak
Liza S. Rovniak, PhD, MPH
Adjunct Assistant Professor
Center for Behavioral Epidemiology & Community Health
Graduate School of Public Health, San Diego State University
San Diego, CA 92123
Phone: 8585054770, ext. 152; Fax: 8585058614
Email: [log in to unmask]
 CLASSL list. Instructions: http://www.classificationsociety.org/csna/lists.html#classl

CLASSL list.
Instructions: http://www.classificationsociety.org/csna/lists.html#classl
