Title:      Data Experiments:  Model Specifications as Treatments

Authors:    Kevin A. Clarke

Entrydate:  2007-07-16 11:26:13

Keywords:   Nonnested model testing, randomized complete block
designs, nonparametrics

Abstract:   This paper introduces the first model discrimination
test for three or more competing nonnested models.  The key to
the approach is treating rival model specifications as
experimental treatments applied to a set of observations. 
Viewed in this way, competing specifications can be tested using
techniques designed for analyzing multiple related samples.  To
this end, two such procedures are adapted for the purpose of
comparing three or more nonnested model specifications. The
models to be compared may be nonnested either in their
covariates or in their functional forms.
The tests are straightforward and can be implemented using
standard statistical software.  The usefulness of the tests is
demonstrated through real-world applications drawn from
comparative politics and international relations.

http://polmeth.wustl.edu/retrieve.php?id=705