Sparse Regression Quantile Fitting with Weights

Sparse Regression Quantile Fitting with Weights

rq.fit.sfn_start_val(
  X,
  y,
  tau = 0.5,
  rhs = (1 - tau) * c(t(a) %*% rep(1, length(y))),
  control,
  sv,
  weights = NULL,
  lambda,
  ...
)

Arguments

X

structure of the design matrix X stored in csr format

y

outcome vector

tau

desired quantile

rhs

the right-hand-side of the dual problem; regular users shouldn't need to specify this, but in special cases can be quite usefully altered to meet special needs. See e.g. Section 6.8 of Koenker (2005).

control

control parameters for fitting routines: see quantreg::sfn.control()

sv

starting value for optimization, useful when bootstrapping

weights

Optional vector of weights for regression

lambda

ignored

...

other parameters, ignored

Details

A wrapper around the rq.fit.sfn function from the quantreg package, extended to allow for a user-supplied starting value and weights