A Random Coefficient Var Transition Model of the Changes in Land Use in the Brazilian Amazon

Authors

  • Lykke E. Andersen Centre for Non-linear Economic Modelling, Dept. of Economics, Univ. of Aarhus, Danmark. This work was done while the first author was visiting the Dept. of Economics, Univ. of California, San Diego, and the hospitality of the department is gratefully ackn
  • Clive W.J. Granger Department of Economics, University of California, San Diego, USA. The research is supported by NSF Grant SBR-930081 and is part of a larger project investigating the dynamics and economics of deforestation.
  • Eustáquio J. Reis lnstitute for Applied Economic Research, Rio de Janeiro.

DOI:

https://doi.org/10.12660/bre.v17n11997.2868

Keywords:

Short panels, random coefficients, transition models, Monte Carlo simulation, deforestation

Abstract

This paper shows how a VAR transition model can be estimated from panel data, taking into account that the transition coefficients may not be identical across regions. The method is applied to a model of dynamic land use changes in Brazil's Amazon region. The model is intended to shed light on the deforestation process in the world's largest remaining rain forest.

Downloads

Published

1997-05-01

Issue

Vol. 17 No. 1 (1997)

Section

Articles