Empirical economic model discovery and theory evaluation

Working paper

Economies are so high dimensional and non-constant that many features of models cannot be derived by prior reasoning, intrinsically involving empirical discovery and requiring theory evaluation. Despite important differences, discovery and evaluation in economics are similar to those of science. Fitting a pre-specified equation limits discovery, but automatic methods can formulate much more general models with many variables, long lag lengths and non-linearities, allowing for outliers, data contamination, and parameter shifts; select congruent parsimonious-encompassing models even with more candidate variables than observations, while embedding the theory; then rigorously evaluate selected models to ascertain their viability.

Authors: Hendry, D

• Publication status: Published
• Publisher: University of Oxford
• Series: Department of Economics Discussion Paper Series
• Publication date: 2011-02-01
• Paper number: 529
• Keywords: autometrics; model selection; theory evaluation; empirical discovery