I fit a quantile regression using quantreg:::rq on clustered data. I use the Huber sandwich estimator to obtain cluster-corrected standard errors, which is indicated by the se = 'nid' argument in summary.rq.
But here's my confusion:
q_1 <- rq(y ~ y, tau = .5, data = data)
summary.rq(q_1, se = 'nid')
Shouldn't there be an argument to specify on which variable is my data clustered? Thanks for the help!
*Below is a similar question to mine, but it doesn't resolve my specific confusion:
