conjoint survey and binary logistic regression

Moderators: statman, Analyst Techy, andris, Fierce, GerineL, Smash

Pete_R
Posts: 1
Joined: Sat Mar 14, 2009 3:11 pm

conjoint survey and binary logistic regression

Postby Pete_R » Sat Mar 14, 2009 6:24 pm

Hello:

I believe I understand I will be using binary logistic regression to generate the relative worth of each attribute that goes into a respondent's choosing or not choosing an option. How do I code this so that I can run the analysis. (I don't have the SPSS conjoint module, so I will be using binary logistic regression I believe.)

If question 1 is:
Choose one of the 3 options:
Option 1 (brand a, low price, small size)
Option 2 (brand b, low price, medium size)
Option 3 (brand c, medium price, large size)

Say they choose for question 1: option 2.

Do I code it thus (to generate the regression coefficients for the entire set of respondents)

respondent 1, question 1, did not choose, a, not b, not c, 1, not 2, not 3, 1, not 2, not3
repondent 1, question 1, did choose, not a, b, not c, 1, not 2, not 3, not 1, 2, not 3
respondent 1, question 1, did not choose, not a, not b, c, not 1, 2, not 3, not 1, not 2, 3

That is:
1, 1 0 1 0 0 1 0 0 1 0 0
1, 1 1 0 1 0 1 0 0 0 1 0
1, 1 0 0 0 1 0 1 0 0 0 1

If I am on the right track I will ask about reference value next!
statman
Administrator
Posts: 2757
Joined: Tue Jun 12, 2007 12:08 pm
Location: Florida, USA

Re: conjoint survey and binary logistic regression

Postby statman » Sun Mar 15, 2009 6:33 pm

Yes, can take this approach but be prepared for some 'trickery', you have to trick LR. I have some syntax for this somewhere and get back to you
See the note below

NOTE: Please read the Posting Guidelines and always tell us your OS, the SPSS version and information about your study and data!

Statman
Statistical Services

Who is online

Users browsing this forum: No registered users and 1 guest

cron