Preprocessing Algorithm for Quantile Regression
A preprocessing algorithm for the Frisch Newton algorithm for quantile regression. This is one possible method for rq().
rq.fit.pfn(x, y, tau=0.5, Mm.factor=0.8, max.bad.fixup=3, eps=1e-06)
design matrix usually supplied via rq()
response vector usually supplied via rq()
quantile of interest
constant to determine sub sample size m
number of allowed mispredicted signs of residuals
Preprocessing algorithm to reduce the effective sample size for QR problems with (plausibly) iid samples. The preprocessing relies on subsampling of the original data, so situations in which the observations are not plausibly iid, are likely to cause problems. The tolerance eps may be relaxed somewhat.
Returns an object of type rq
Portnoy and Koenker, Statistical Science, (1997) 279-300