Abstract
This paper extends Kelejian and Prucha's 1998 feasible generalized spatial two-stage least squares (FGS2SLS) estimator to account for endogenous variables due to system feedback, given an autoregressive or a moving average error process. An empirical example illustrating the different estimators is proposed. The finite sample properties of the estimators are investigated by means of Monte-Carlo simulations depending of the sample size, the weights matrix, the presence of cross-equation correlation and the nature of the instruments.
Original language | English |
---|---|
Pages (from-to) | 39-62 |
Number of pages | 24 |
Journal | Annales d'Économie et de Statistique |
Issue number | 87/88 |
Publication status | Published - 2007 |
Keywords
- Spatial models
- Monte Carlo simulation
- weights matrix