Have an idea?

Visit Sawtooth Software Feedback to share your ideas on how we can improve our products.

Degrees of freedom in LC

Dear all,

I have a question regarding the degrees of freedom of my study since I do not know exactly how to determine them.
I've run a LC analysis with 5 attributes with three levels each. My optimal solution gives me 4 segments. My sample size is N = 265. Each respondent had to answer 12 choice tasks including 3 stimuli/ product concepts and a none-option. Within these 12 choice tasks, I've included 2 fixed tasks for hold-out prediction.

Can you tell me how to calculate the number of parameters and degrees of freedom exactly? I think for the number of parameters, I get (5x2 +1)x4 segments = 44 parameters. Is that correct?

I am looking forward to hear from you soon :-)
Best regards!
asked Aug 5, 2017 by briniminii (490 points)
retagged Aug 5, 2017 by Walter Williams

1 Answer

0 votes
I think you are correct, yes.
answered Aug 6, 2017 by Keith Chrzan Platinum Sawtooth Software, Inc. (52,450 points)
okay thank you! But do you know how to calculate the degrees of freedom then? Because the number of parameters estimated is not equal to df I thought.
I need that value to get my critical value for chi-squared.

Thanks a lot for your help!