Have an idea?

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

"How to identify bad IDs in a MaxDiff" data, before modelling

How to identify a genuine response in the MaxDiff question before we do any analysis on them    

i.e. Random click, completed the questions less than particular time, or taken a large amount of time to complete, etc.  these are some of the cases that are there in the data. how will i know for sure if these are genuine respondents or bad IDs ???
asked Mar 23 by anonymous

1 Answer

0 votes
My colleague Bryan Orme posted a nice article I think you'll find helpful.  It's on our LinkedIn Sawtooth Software User's Group, here:  https://www.linkedin.com/pulse/identifying-consistency-cutoffs-identify-bad-respondents-orme/?trackingId=a0B6L7fbmbVa5qjSUyYOdA%3D%3D
answered Mar 23 by Keith Chrzan Platinum Sawtooth Software, Inc. (90,575 points)