Have an idea?

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

What coding is used for direct anchor method?

I am trying to replicate the Sawtooth results from the aggregate logit  maxdif model, with a direct binary anchor.  Exporting the data into Stata  I can replicate results exactly for the best/worst questions alone.

But when I add the 2 additional tasks to reflect the anchor (as per Lattery 2011) I cannot replicate the results.  Looking at the LL for the null model estimated by Sawtooth, I am wondering if the implementation is actually "..the binary version where each attribute was compared with a zero vector." (in my case that would add 12 additional tasks, not 2).  Is it possible to confirm which implementation is used?

Update:  worked out more quickly than I expected how to generate the data in that form, and that does appear to be the case: when I use the binary version I exactly replicate the results.
asked Nov 13, 2015 by michael

1 Answer

0 votes
All items are compared to the anchor in pairwise comparisons: so if you have 12 items there are 12 additional tasks to append for each respondent.
answered Nov 13, 2015 by Bryan Orme Platinum Sawtooth Software, Inc. (132,290 points)