A goal programming-constrained regression review of the Bell System breakup

Goal programming and constrained regression methodologies are applied to empirical data collected during the breakup of the Bell System. The results of these methodologies reverse the findings of previous studies conducted with econometric methods. The studies that had used econometric methods reported that the evidence failed to support the contention that the Bell System was a natural monopoly. Given the important policy implications of the Bell System breakup, similar studies that are performed in the future should be conducted by people from different disciplines who have the ability to check each other's methodologies. A 12-page rejoinder by David S. Evans and James J. Heckman follows the article.