Abstract
We investigate the common conjecture in applied econometric work that the inclusion of spatial fixed effects in a regression specification for a single cross-sectional data set removes spatial dependence. We demonstrate analytically and by means of a series of simulation experiments how evidence of the removal of spatial autocorrelation by spatial fixed effects may be spurious when the true data generating processes (DGP) takes the form of a spatial lag or spatial error dependence. In addition, we also show that spatial fixed effects correctly remove spatial correlation only in the special case where the dependence is group-wise, with all observations in the same group as neighbours of each other.
Original language | English (US) |
---|---|
Pages (from-to) | 3-17 |
Number of pages | 15 |
Journal | Papers in Regional Science |
Volume | 92 |
Issue number | 1 |
DOIs | |
State | Published - Mar 2013 |
Keywords
- Spatial autocorrelation
- Spatial econometrics
- Spatial externalities
- Spatial fixed effects
- Spatial interaction
- Spatial weights
ASJC Scopus subject areas
- Geography, Planning and Development
- Environmental Science (miscellaneous)