Hole's WTP command with interactions

[Julia Jones]

Hello Statalisters,

I am analyzing discrete choice data using Arne Risa Hole's user-written command mixlogit and his post-estimation command wtp. I would like to estimate mean willingness to pay as well as Krinsky-Robb confidence intervals for an interaction term. The interaction term is between a case-specific dummy variable for senior status (0 if respondent is younger than fifty, 1 if respondent is 50 or older), and a continuous variable distance (miles to distribution facility). Does anyone have suggestions for how best to do this?

Best,

Julia Jones

Department of Natural Resources and the Environment
University of New Hampshire

[Julia Jones]

Bumping in hopes of a response!

[Laura Andreea]

Hi! Did you find a socultion? I am having the same question.

[Emmanuel Teitelbaum]

Same question here. I have found a couple of articles that do this. One does it manually:

https://www.ncbi.nlm.nih.gov/pmc/art...cmh-21-268.pdf

Another uses the -wtpcikr- to calculate Krinsky and Robb CIs:

https://www.mdpi.com/2071-1050/10/6/2061

However, I have not figured out how to implement the calculation using Krinsky and Robb CIs. Another Stata user reports finding a way to do it but does not share that part of his code:

https://www.statalist.org/forums/for...h-interactions