DSC 410/510 - Multivariate Statistical Methods

Assignment 3 (deadline: 4pm on Monday, October 11)

Practical matters

Jobs example (continued):

• Create a design for the jobs example by following steps 1 and 2 in "Jobs Example from class" from the handouts page. This uses the SAS software available in the lab. Note that the design that you get may not be the same as the design which was used for assignment 2.
• Run a conjoint analysis for the jobs example by following steps 3, 4, and 5 in the "Jobs Example from class" handout. Since your design may be different to the one used in assignment 2, don't just re-use your earlier ranks.
• Investigate the effect of reducing the range of the levels for Salary. For example, change the levels from "50K, 60K, 70K, 80K" to "62K, 64K, 66K, 68K." Then create a design (using "SAS"), rank the stimuli, enter your ranks (using "Excel"), and analyze your data (using "SAS"). What happens to the "Conditional Relative Importance" of Salary in the analysis of your rankings? Why do you think this happened? Send an e-mail to ipardoe at lcbmail.uoregon.edu with a brief answer to this question.