Aggregation without Separability: Tests of the United States and Mexican Agricultural Production Data
and formerly a graduate assistant at Texas A…M University
This manuscript reports research conducted by the Texas Agricultural Experiment Station, Texas A…M University System. Appreciation is extended to participants at the 1998 AAEA meetings, especially Jim Eales and Ron Mittelhammer, seminar participants at Texas A…M University, the University of Nevada at Reno, and the University of Tennessee, and to two anonymous reviewers for constructive comments on earlier versions of the paper. Appreciation is also extended to Arthur Lewbel for clarifying several issues related to the paper.
Abstract
The generalized composite commodity theorem (GCCT) and testing procedure is extended to test for consistent aggregation of the United States and Mexican agricultural production data in each category for which earlier tests rejected homothetic separability. Nonrejected GCCT and separability hypotheses provide empirical support for aggregating all the United States agricultural outputs into as few as two categories: crops and livestock. Mexican agricultural outputs also can be aggregated into as few as two categories. Support for aggregating all outputs into a single category is ambiguous in both countries and is only provided by the GCCT.
