Geoscience Reference
In-Depth Information
SAR is favored
SAR
SAR
OLS
Not reject
:
=0
:
=0
Not reject
Not
sasfied
Not
reject
Reject OLS
SDM
OLS
OLS
LR
Test
LM
Test
=
+
+
+
SDM
=
+
=
+
+
:
=0
reject
:
=0
reject
Not reject
SDM
:
+
=0
SEM is favored
SEM
SDM
SLX
SEM
:
=0
Not reject
Fig. 10.3
Elhorst spatial model testing procedure.
Note
: SAR, SEM and SLX represent Spatial
autoregressive model, Spatial error model and Spatial lagged X model. LM test and LR test
represent Lagrange multiplier test and Likelihood ratio test
In this study, we follow the Elhorst spatial model procedure to test which spatial
model is preferred technically. Table
10.2
illustrates the specific spatial model form
and effect for each industry from Elhorst's routine. Hausman test suggests that
spatial time fixed effect needs to be considered for most of the economic sectors.
The spatial estimations for trade and warehousing do not include any effect. The
pipeline sector is identified as needing to be controlled for both spatial fixed and
time fixed effects.
A key function of spatial analysis is to investigate the spatial effects of factor
substitution among different states. Because the spatial information of neighboring
regions is added in the form of a spatial weight matrix, SDM is endowed with the
capacity to investigate spillover effects from total effects (LeSage and Pace
2009
).
As a result, three types of impacts can be estimated through the spatial model:
average direct impact, average indirect impact and average total impact (LeSage
and Pace
2009
). The first impact measures the influences of the explanatory
variables that come from the same geographic unit as the dependent variable. The
second impact, the indirect effect or spillover effect, measures the influence of
explanatory variables that come from different geographic units. The third impact,
total effect, consists of both the direct impact and indirect impact.
10.5.4 Step 4 SECGE
During step 4, a CGE model with an integration of spatial econometric estimates is
established. The structure of CGE model has been discussed in Sect.
10.3
. The
elasticity of factor substitution was estimated under both non-spatial and spatial
econometric models in step 2 and 3. These are the estimates utilized respectively for
the CES production function in the CGE. The spatial econometric CGE (SECGE) is
the second type of integration. Given the fact that the elasticity of factor substitution
is not assumed or calibrated in this equilibrium model, the estimates based on
historical data under the spatial econometric approach is expected to be more
realistic for policy simulation. In addition, compared to the non-spatial econometric
