DSC 410/510 - Multivariate Statistical Methods
Assignment 7 (deadline: 4pm on Monday, October 25)
Practical matters
Jobs example (continued):
Work through "jobspw3.sas" (available from the handouts page of the class web-site) which
provides SAS code and instructions for running hierarchical and
non-hierarchical cluster analyses on the jobs example part-worths
(available in the "jobspw3.xls" spreadsheet available from the data page). In particular:
run Ward's minimum variance cluster analysis, including
producing a dendogram
run a 2-cluster non-hierarchical analysis using hierarchical
cluster means as initial seeds
profile the 2-cluster non-hierarchical solution and assess
significant differences
profile the solution on additional variables not used in the
clustering procedure
produce a profile plot in Excel which includes the average
partworths from the conjoint exercise for each cluster
Send an e-mail to ipardoe at
lcbmail.uoregon.edu with a brief description of how you would
characterize the main differences between the two clusters (both in
terms of the part-worths from the conjoint analysis, as well as the
demographic information on age, work experience, salary expectation,
and student status).
© 2004, Iain Pardoe, Lundquist College of Business,
University of Oregon
Last updated October 20, 2004