WTP computation and coding

Question

Dear all,

my price attribute (A1) solely has quantitative levels. The other two attributes (A2; A3) have one qualitative level and three quantitative levels each. Supposing that I dummy code all three attributes:
- Is it possible to tell how much people are willing to pay for e.g. level 1 of A2?
- Is it possible to answer the question how much more people are willing to pay for a shift from level one to level two of A2 or A3?
- Is it possible to interpolate between the levels of my attributes even if they are dummy coded or would that only be possible if I code at least the price attribute linear (trying to answer the question how much more people are willing to pay for one unit more of A2?)
- Does dummy coding of all attributes allow to answer the question how much more probable it is that an alternative is choosen if the price raises by 1% (or does at least the price need to be linear coded for this computation)?
- Generally: an attribute that contains quantiative and qualitative levels always needs to be dummy/effects coded, right?
Thanks in advance!

Answer 1

Willingness to Pay (WTP) has many ways to compute it offered in the literature...some better than others.  Sawtooth Software has an approach that is part of its market simulator: https://sawtoothsoftware.com/resources/technical-papers/estimating-willingness-to-pay-in-conjoint-analysis

You cannot tell how much people are willing to pay for a single level alone (e.g., level 1 of A2) with standard conjoint analysis (CBC).  You can only tell how much people are willing to pay for one level of an attribute compared to another level of the same attribute.

You can tell how much people are willing to pay for a shift from level 1 to level 2 or 3 of that SAME attribute.

It is possible to linear interpolate between attribute levels: both for the price attribute and the other attributes.  

With dummy-coding, you can linear interpolate between the utilities of adjacent levels.  

An attribute that has mixed quantitative and qualitative levels could by dummy-effects coded.  Or, I think a fancier coding approach could offer a mixed approach (that dummy-coded the first level and linear coded the quantitative levels.  That would be just a twist on the "piecewise coding" approach.