Have an idea?

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

How to calculate confidence levels for HB with covariates?

Hello everyone,

I am currently analyzing the results of my first ACBC study. I am especially interested in how certain personality characteristics (e.g. level of
extraversion) influence the preferences for my  attributes. Therefore, I am including theses personality  characteristics as covariates in my HB model. The article by Orme &  Howell (2009) was very helpful for setting up the model. In order to determine which covariates have a significant impact on the utilities, I am checking the alpha file based on the rule by Orme & Howell: “When the percent of draws that are positive is >95% or <5%, it suggests that these covariate weights are significantly different from zero, at or better than the 90% confidence level (two-sided test).”

However, I do not understand how the authors come to that conclusion. What kind of test was done, and how? Are there also benchmarks for stricter confidence levels (e.g. 95 %)?

Thanks and best,
asked Sep 24, 2018 by Stefanie (120 points)
retagged Sep 24, 2018 by Stefanie

Your answer

Please only use this to answer the original question. Otherwise please use comments.
Your name to display (optional):
Privacy: Your email address will only be used for sending these notifications.
Anti-spam verification:

To avoid this verification in future, please log in or register.