A popular procedure for benefit segmentation based on conjoint experiments has been to estimate individual-level port worths and then form nonoverlapping clusters of consumers with similar estimates. Rather than using these estimates as the criteria for clustering, the least squares procedure...

We report the results of experiments designed to test recent theories of vertical foreclosure. Consistent with the theory, the upstream firm has more difficulty commiting to supply the monopoly quantity in treatments with non-integration and secret contracts than in either treatments with...