[Limdep Nlogit List] Test for differences in marginal wtp between samples

[Lars Persson]

Dear all
I have a split sample choice experiment and would like to test if there is a significant difference in marginal wtp between the samples. So far, the model specification is RPL in preference space with normal distributions except for the cost attribute (fixed). I have seen people doing the complete combinatorial test suggested by Poe et al. 2005, is this still the recommendation? If so, I would really need and appreciate practical guidance on how to do this.

Related to this issue, I have calculated the marginal wtp’s as the ratio of coefficients using the Wald command. I know it is recommended to use the ;wtp command to get the individual wtp’s, but how would that affect the use of the ”Poe test”? Any alternatives?

Any advise or help related to these topics are deeply appreciated.

Lars