Abstract
For spatial regressions with sinusoidal surfaces, the ordinary least squares estimator (OLSE) is shown to be asymptotically as efficient as the generalized least squares estimator (GLSE) in that the covariance matrices of the two estimators have the same nontrivial limit under the same normalization.
Original language | English |
---|---|
Pages (from-to) | 247-258 |
Number of pages | 12 |
Journal | Metrika |
Volume | 56 |
Issue number | 3 |
DOIs | |
State | Published - 2002 |
Keywords
- Efficiency
- GLSE
- OLSE
- Sinusoidal surface
- Spatial regression