More refined trade-off analysis

yhoriuchi / projoint

A package for a more general, more straightforward, and more creative conjoint analysis

https://yhoriuchi.github.io/projoint/

Other

10 stars 0 forks source link

More refined trade-off analysis #29

Open yhoriuchi opened 1 year ago

yhoriuchi commented 1 year ago

Eventually, for choice-level analysis, we should allow users to specify any combination of attribute levels using AND and OR. For example, the arguments should be something like the following:

.profile1 = "(att1:level1 OR att1:level2) AND att2:level1"
.profile2 = "(att1:level3) AND (att2:level2 OR att3:level3)"

yhoriuchi commented 1 year ago

I now think that this is one of the top priorities. Currently, users need to specify both attributes and levels for a profile choice and a profile not-chosen. Too many things to set. The function will be simpler and allow users to specify any combination of attribute-levels (using any number of AND and OR) for choice-level analysis. What do you think, @thegaryking and @aaronrkaufman ?

aaronrkaufman commented 1 year ago

I am not sure I understand this, but I'd like to talk through it!

yhoriuchi commented 1 year ago

Consider that you want to compare:

A Republican candidate who is white
A Democratic candidate who is not white (Asian, Hispanic, or Black)

for non-white Republican respondents. In this case, you need to use two attributes (race, party). You also need to use "Asian OR Hispanic OR Black).

Currently, we cannot calculate the choice-level MMs, which involve more than one attribute.