| hccm {car} | R Documentation |
Calculates heteroscedasticity-corrected covariance matrices for unweighted linear models. These are also called ``White-corrected'' covariance matrices.
hccm(model, ...)
hccm.lm(model, type=c("hc3", "hc0", "hc1", "hc2"))
hccm.default(model, ...)
model |
an unweighted linear model, produced by lm. |
type |
one of "hc0", "hc1", "hc2", or "hc3"; the
first of these gives the classic White correction. The others are described in
Long and Ervin (2000). |
... |
arguments to pass to hccm.lm. |
The classical White-corrected coefficient covariance matrix ("hc0") is
V(b) = inv(X'X) X' diag(e^2) X inv(X'X)
where e^2 are the squared residuals, and X is the model matrix. The other methods represent adjustments to this formula.
The function hccm.default simply catches non-lm objects.
The heteroscedasticity-corrected covariance matrix for the model.
John Fox jfox@mcmaster.ca
Long, J. S. and Ervin, L. H. (2000) Using heteroscedasity consistent standard errors in the linear regression model. The American Statistician 54, 217–224.
White, H. (1980) A heterskedastic consistent covariance matrix estimator and a direct test of heteroskedasticity. Econometrica 48, 817–838.
options(digits=4) data(Ornstein) mod<-lm(interlocks~assets+nation, data=Ornstein) Var(mod) ## (Intercept) assets nationOTH nationUK nationUS ## (Intercept) 1.079e+00 -1.588e-05 -1.037e+00 -1.057e+00 -1.032e+00 ## assets -1.588e-05 1.642e-09 1.155e-05 1.362e-05 1.109e-05 ## nationOTH -1.037e+00 1.155e-05 7.019e+00 1.021e+00 1.003e+00 ## nationUK -1.057e+00 1.362e-05 1.021e+00 7.405e+00 1.017e+00 ## nationUS -1.032e+00 1.109e-05 1.003e+00 1.017e+00 2.128e+00 hccm(mod) ## (Intercept) assets nationOTH nationUK nationUS ## (Intercept) 1.4808521 -1.640e-05 -1.445e+00 -1.460e+00 -1.455e+00 ## assets -0.0000164 2.425e-09 1.079e-05 1.324e-05 1.161e-05 ## nationOTH -1.4451983 1.079e-05 6.743e+00 1.432e+00 1.430e+00 ## nationUK -1.4600207 1.324e-05 1.432e+00 3.722e+00 1.440e+00 ## nationUS -1.4550976 1.161e-05 1.430e+00 1.440e+00 1.840e+00