On the power of the generalized Moran contiguity coefficient in testing for spatial autocorrelation among regression disturbances

Non‐nested Tests on the Weight Structure in Spatial Autoregressive Models: Some Monte Carlo Results*

“…(2) the same number of observations with p as 0.25 (low degree of spatial connectivity); (3) a sample of 38 observations with p as 0.75. The specific spatial configurations used are based on an actual system and not on a more traditional idealized regular lattice structure [see also Bartels and Hordijk (1977), and Brandsma and Ketellapper (1979) for the use of actual spatial systems in simulation studies]. Since the spatial accessibility is considered as the formal basis for the dependence structure, and not a spatial lag based on a lattice system, the distinction between regular and irregular networks becomes largely irrelevant.…”

Lagrange Multiplier Test Diagnostics for Spatial Dependence and Spatial Heterogeneity

“…Recent overviews of the relevant issues can be found in, among others, Cliff andOrd (1973, 1981), Bartels and Hordijk (1977), Haining (1978), Brandsma and Ketellapper (1979), Bennett (1979), Hordijk (1979), Griffith (1980Griffith ( ,1983, Anselin (1980Anselin ( ,1984Anselin ( , 1987, Blommestein (1983), Upton and Fingleton (1985).…”

Properties of Tests for Spatial Dependence in Linear Regression Models

“…As illustrated in Table 1, only two of these, Bartels and Hordijk (1977) and Brandsma and Ketellapper (1979) focus explicitly on the power of tests for spatial error autocorrelation. Other studies address the influence of boundary effects (Grifith and Amrhoin 1983;Grifith 1985Grifith , 1988a, and the choice of the spatial weights matrix (Stetzer 1982;Anselin 1986a).…”