Quantile Regression Fitting by Gradient Search

Share:

Description

This function controls the arguments to be passed to routines written in C for LQM estimation. The optimization algorithm is based on the gradient of the Laplace log–likelihood (Bottai, Orsini and Geraci, 2013).

Usage

1
lqm.fit.gs(theta, x, y, weights, tau, control)

Arguments

theta

starting values for the regression coefficients.

x

the model matrix.

y

the model response.

weights

the weights used in the fitting process.

tau

the quantile to be estimated.

control

list of control parameters used for optimization (see lqmControl).

Details

See argument fit in lqm for generating a list of arguments to be called by this function.

Value

An object of class list containing the following components:

theta

a vector of coefficients.

scale

the scale parameter.

gradient

the gradient.

logLik

the log–likelihood.

opt

number of iterations when the estimation algorithm stopped.

.

Author(s)

Marco Geraci

References

Bottai M, Orsini N, Geraci M (2014). A Gradient Search Maximization Algorithm for the Asymmetric Laplace Likelihood, Journal of Statistical Computation and Simulation, 85, 1919-1925.

See Also

lqm

Examples

1
2
3
4
5
6
7
set.seed(123)
n <- 500
test <- data.frame(x = runif(n,0,1))
test$y <- 30 + test$x + rnorm(n)
lqm.ls <- lqm(y ~ x, data = test, fit = FALSE)

do.call("lqm.fit.gs", lqm.ls)

Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker.