Name: Jim Mott
Home office: Chicago, IL
About Jim: Jim has nearly 20 years experience with SPSS Inc. From 1984 to 1998, he served as technical writer, technical support specialist, and internal trainer. Jim has been a senior education consultant since 1998. He received a BA from Knox College and an MA and PhD from the University of Illinois at Chicago. In his spare time, Jim enjoys playing classical piano, attending the opera, playing golf, and hiking and camping.
Regrouping fields in Clementine 8.0
For market basket, cluster, and similar types of analysis, it is often advantageous to collapse specific set variable categories into more general ones. For example, a supermarket may have hundreds or thousands of unique items. Rather than examine the associations between, for example, the purchase of chicken and each of a long list of vegetables, it may be more useful to reclassify all meat items into one category and all vegetable items into another. Once you collapse the variables, you can use the set to flag node to create multiple flag variables from each of the new set values, which the association or cluster analysis nodes can then use as input fields.
The reclassify node (new in Clementine 8.0) makes it easy to regroup fields such as the one described above. You can either replace the original values for a field, or create a new field and retain the original, which may be a safer approach.
To reclassify a field:
Figure 1 is an example of how the reclassify node should look when you are finished (click on the image below to enlarge):
We offer SPSS courses at locations around the world.
Find a course in the location nearest to you.
Predictive Analytics
can make your organization
more
successful
Resources