Dear all,
I am trying to design a Wald test to verify whether some coefficients are
statistically equal.
I would like to test not only whether they are jointly equal for a given
quantile, but for a range of quantiles. Hence, I need to extract the
variance-covariance matrix among the coefficients of a rq object:
qf2 <- summary(rq(wb2 ~ apv2 + vol2, tau=c(a1,a2)), cov=TRUE)
I need not only the varcov matrix between the coefficients beta_0, beta_1,
beta_2, but also between beta_0(a1) and beta_0(a2), and so on... (i.e., across
quantiles)
it is not a simple anova.rq test because I am comparing two different samples.
The samples are independent, so, the varcov matrix between them is zero.
However, I need to find the varcov between the coefficients across quantiles
for each sample. Then, i will include the matrix in my Wald Test.
I have tried the command qf2[[3]], but it does not work.
Is there any other command that gives me the varcov between all those
coefficients across quantiles?
Thanks a lot!
Julia
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
