Forum Moderators: DixonJones
One of the problems with this analysis is going to be comparing the KW patterns for purchases to the KW patterns of those who didn't purchase. If you can't do that, you can't get a handle on causality at all.
I know that big companies do this all the time and most of them use an ordinary stats program like SAS or SPSS. The data collection shouldn't be too hard. Getting an accurate modeling of the data will be.