rqbulk: Quantile regression for bulk of distribution

In gbstat/tailqr: 'Fit Mixture of Quantile Regression and GPDs'

Description

Fit quantile regression to bulk of data and extract exceedances

Usage

rqbulk(y, dates, df.lf, df.hf, taus, Xb = NULL, b.formula = ~b.lf + b.hf +
  b.lf:b.hf, threshold.tau = NULL, return.basis = TRUE,
  return.yhat = TRUE, return.excd = FALSE, type = c("upper", "lower"))

Arguments

y	response vector
dates	vector of dates of each observation
df.lf	natural spline degrees of freedom on date
df.hf	periodic basis spline degrees of freedom on the day of the year
taus	quantiles to estimate
Xb	(optional) matrix of basis functions. Each basis function is in a separate column.
b.formula	basis formula. Should be function of b.lf and b.hf
threshold.tau	quantile above or below which taus are to be interpreted conditionally for distributions exceeding threshold.tau (either below or above).
return.basis	(logical) should the basis matrix be returned?
return.yhat	(logical) should matrix of predicted quantiles (see taus) be returned?
return.excd	(logical) should vector of exceedances of highest quantile be returned?
type	one of "upper" or "lower" if tail tau quantiles should be handled separately.

Value

A list containing the basis matrix (Xb), fitted quantiles (yhat), QR basis coefficients (betas), lower and upper exceedances, dates, indices, and thresholds (lexcd, lexcd.dates, lexcd.id, lthresh) and (uexcd, uexcd.dates, uexcd.id, uthresh)

gbstat/tailqr documentation built on May 8, 2019, 5:42 p.m.