lsem {spmoran} | R Documentation |
Low rank spatial error model (LSEM) estimation
Description
This function estimates the low rank spatial error model.
Usage
lsem( y, x, weig, method = "reml" )
Arguments
y |
Vector of explained variables (N x 1) |
x |
Matrix of explanatory variables (N x K) |
weig |
eigenvectors and eigenvalues of a spatial weight matrix. Output from |
method |
Estimation method. Restricted maximum likelihood method ("reml") and maximum likelihood method ("ml") are available. Default is "reml" |
Value
b |
Matrix with columns for the estimated coefficients on x, their standard errors, t-values, and p-values (K x 4) |
s |
Vector of estimated variance parameters (2 x 1). The first and the second elements denote the estimated rho parameter (sp_lambda) quantfying the scale of spatial dependent process, and the standard error of the process (sp_SE), respectively. |
e |
Vector whose elements are residual standard error (resid_SE), adjusted conditional R2 (adjR2(cond)), restricted log-likelihood (rlogLik), Akaike information criterion (AIC), and Bayesian information criterion (BIC). When method = "ml", restricted log-likelihood (rlogLik) is replaced with log-likelihood (logLik) |
r |
Vector of estimated random coefficients on the spatial eigenvectors (L x 1) |
pred |
Vector of predicted values (N x 1) |
resid |
Vector of residuals (N x 1) |
other |
List of other outputs, which are internally used |
Author(s)
Daisuke Murakami
References
Murakami, D., Seya, H. and Griffith, D.A. (2018) Low rank spatial econometric models. Arxiv.
See Also
Examples
require(spdep)
data(boston)
y <- boston.c[, "CMEDV" ]
x <- boston.c[,c("CRIM","ZN","INDUS", "CHAS", "NOX","RM", "AGE",
"DIS" ,"RAD", "TAX", "PTRATIO", "B", "LSTAT")]
coords<- boston.c[,c("LON", "LAT")]
weig <- weigen( coords )
res <- lsem(y=y,x=x,weig=weig)
res