Robust standard errors in spatial error models

1 message
Open this post in threaded view
|

Robust standard errors in spatial error models

Hello everybody,

I have estimated a spatial error model by means of the lagsarlm() function. The Breusch-Pagan test for spatial models (bptest.sarlm()) shows heteroskedasticity evidence. I want to estimate robust standard errors, but the functions I have looked at only work with lm type objects. In page 23 in the spdep manual it is stated that "it is also technically possible to make heteroskedasticity corrections to standard error estimates by using the “lm.target” component of sarlm objects – using functions in the lmtest and sandwich packages.", and gives an example that honestly I do not understand (what is \$tary and \$tarX? what is the lm.target component? where are they documented?). I have adapted the example to my case, obtaining an estimated model with its corresponding coefficients, standard errors, etc. My question is: is this correct? Are these standard errors already robust under heteroskedasticity?

Best

Javi

PD: below you can see the piece of code and the generated output

reg.SLM <- lagsarlm(precio_m2~z1+z2+z3+z4+z5+z6+z7+z8+z9+z10-1,

data=datos,W_n,method="eigen",  tol.solve=1.0e-20)

lm.target <- lm(reg.SEM\$tary ~ reg.SEM\$tarX - 1)

if (require(lmtest) && require(sandwich)) {

coeftest(lm.target, vcov=vcovHC(lm.target, type="HC0"), df=Inf)

}

z test of coefficients:

Estimate Std. Error z value  Pr(>|z|)

reg.SEM\$tarXI(x - lambda * WX)z1       1489.27593  124.86303 11.9273 < 2.2e-16

reg.SEM\$tarXI(x - lambda * WX)z2       1471.24060  135.03910 10.8949 < 2.2e-16

reg.SEM\$tarXI(x - lambda * WX)z3       1646.50753  126.03324 13.0641 < 2.2e-16

reg.SEM\$tarXI(x - lambda * WX)z4       1615.11404  232.94826  6.9334 4.110e-12

reg.SEM\$tarXI(x - lambda * WX)z5       1947.56387  149.28017 13.0464 < 2.2e-16

reg.SEM\$tarXI(x - lambda * WX)z6       1903.80428  132.62287 14.3550 < 2.2e-16

reg.SEM\$tarXI(x - lambda * WX)z7       1943.40961  118.29268 16.4288 < 2.2e-16

reg.SEM\$tarXI(x - lambda * WX)z8       2576.77441  144.33295 17.8530 < 2.2e-16

reg.SEM\$tarXI(x - lambda * WX)z9       3037.47241  215.77036 14.0773 < 2.2e-16

reg.SEM\$tarXI(x - lambda * WX)z10      3976.81752  260.71406 15.2536 < 2.2e-16

reg.SEM\$tarXI(x - lambda * WX)z1       ***

reg.SEM\$tarXI(x - lambda * WX)z2       ***

reg.SEM\$tarXI(x - lambda * WX)z3       ***

reg.SEM\$tarXI(x - lambda * WX)z4       ***

reg.SEM\$tarXI(x - lambda * WX)z5       ***

reg.SEM\$tarXI(x - lambda * WX)z6       ***

reg.SEM\$tarXI(x - lambda * WX)z7       ***

reg.SEM\$tarXI(x - lambda * WX)z8       ***

reg.SEM\$tarXI(x - lambda * WX)z9       ***

reg.SEM\$tarXI(x - lambda * WX)z10      ***

---

Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

 JAVIER GARCÍA  Departamento de Economía Aplicada III (Econometría y Estadística)Facultad de Economía y Empresa (Sección Sarriko)Avda. Lehendakari Aguirre 8348015 BILBAOT.: +34 601 7126 F.: +34 601 3754

_______________________________________________
R-sig-Geo mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo