[R] How to transform OLS covariance matrix to White standard errors?

2012-05-26 Thread Dunken
Hi! I am working with a regression of a log-log model that suffers from heteroskedasticity. I have calculated the "White standard errors". I would like to use these "White standard errors" in a RESET test instead of the originally OLS standard errors calculated by the regression. How can I transfo

[R] Using robust std.errors instead of OLS std.errors in regression

2012-05-25 Thread Dunken
I have to make a robust resettest. I have already calculated the robust standard errors but I don't know how to use these in my resettest. I have made the following code: labmodel2 <- lm(formula = log(L) ~ log(W) + log(K) + log(Y), data=labordat) hc.cv <- hccm(labmodel2, "hc0") hc.cv robusttest <