A spatial weight matrix row-standardized based on first order
 contiguity criterium.

datasets

A collection of functions to test and estimate Seemingly
Unrelated Regression (usually called SUR) models, with spatial structure, by maximum
likelihood and three-stage least squares. The package estimates the
most common spatial specifications, that is, SUR with Spatial Lag of
X regressors (called SUR-SLX), SUR with Spatial Lag Model (called SUR-SLM),
SUR with Spatial Error Model (called SUR-SEM), SUR with Spatial Durbin Model (called SUR-SDM),
SUR with Spatial Durbin Error Model (called SUR-SDEM),
SUR with Spatial Autoregressive terms and Spatial Autoregressive
Disturbances (called SUR-SARAR) and SUR with Spatially Independent Model (called SUR-SIM).
The methodology of these models can be found in next references
Mur, J., Lopez, F., and Herrera, M. (2010) <doi:10.1080/17421772.2010.516443>
Lopez, F.A., Mur, J., and Angulo, A. (2014) <doi:10.1007/s00168-014-0624-2>.

Roman Minguez

spsur

Spatial Seemingly Unrelated Regression Models

Ana Angulo

Fernando A Lopez

Jesus Mur

W function

A row-standardized squared matrix with 3085 rows and columns.
The rows and columns follow the same order than Counties included in
<code><a rd-options="" href="/link/NCOVR?package=spsur&version=1.0.0.2" data-mini-rdoc="spsur::NCOVR">NCOVR</a></code> data frame.

Format

Spatial weight matrix for U.S. Counties — W

A row-standardized squared matrix with 3085 rows and columns.
The rows and columns follow the same order than Counties included in
<code><a rd-options='' href='NCOVR'>NCOVR</a></code> data frame.

W: Spatial weight matrix for U.S. Counties

Description

Usage

Arguments

Format

References