Why limit our discrete choice task to next purchase when we can ask about next ten purchases? It does not seem appropriate to restrict choice modeling to one selection only when repeat purchases from the same choice set&n...

Why limit our discrete choice task to next purchase when we can ask about next ten purchases? It does not seem appropriate to restrict choice modeling to one selection only when repeat purchases from the same choice set&n...

Statistical modeling often begins with the response generation process because data analysis is a combination of mathematics and substantive theory. It is a theory of how things work that determines how we ought to collect and analyze&n...

Sawtooth Software has created a good deal of confusion with its latest sales video published on YouTube. I was contacted last week by one of my clients who had seen the video and wanted to know why I was not using such a powerful technique for me...

After several previous posts introducing item response theory (IRT), we are finally ready for the analysis of a customer satisfaction data set using a rating scale. IRT can be multidimensional, and R is fortunate to have its own package, mirt, with excellent documentation (R.Philip Chalmers). But, the presence of a strong first principal...

Variations on a Theme of Negative Skew and Positive ManifoldNo one familiar with research on customer satisfaction expects to find uncorrelated ratings or symmetric distributions centered toward the middle of the rating scale. There are forces at work that structure the means and correlations among the items from a customer satisfaction questionnaire. On the one hand, unsatisfied customers churn,...

Not every system of independent variables can be decomposed into separate components, each with its own unique contribution. Sometimes our individual variables behave “as a unit” and thus become so entangled that we cannot say where the effect of one variable begins and the effect of another variable ends. In such cases, it might be best to ignore the ...

I wanted to thank those of you who have emailed and commented on my last post and its Link to Item Response Theory Presentations Using R. In the Psychometrics Centre website, it is not until Topic 7 called Unidimensional IRT models for binar...