| EM.qr {ALDqr} | R Documentation |
Quantile Regression Using Asymmetric Laplace Distribution
Description
Return estimating the parameters in a quantile regression
Usage
EM.qr(y, x = NULL, tau = NULL, error = 0.000001 , iter = 2000, envelope=FALSE)
Arguments
y |
vector of responses |
x |
the design matrix |
tau |
the quantile to be estimated, this is generally a number strictly between 0 and 1. |
error |
the covergence maximum error |
iter |
maximum iterations of the EM algorithm. |
envelope |
confidence envelopes for a curve based on bootstrap replicates |
Value
Estimated parameter for a quantile regression fit,standard error, log-likelihood.
Author(s)
Luis Benites Sanchez lbenitesanchez@gmail.com, Christian E. Galarza cgalarza88@gmail.com, Victor Hugo Lachos hlachos@ime.unicamp.br
References
[1] Koenker, R. W. (2005). Quantile Regression, Cambridge U. Press.
[2] Yu, K. & Moyeed, R. (2001). Bayesian quantile regression. Statistics & Probability Letters, 54 (4), 437 to 447.
[3] Kotz, S., Kozubowski, T. & Podgorski, K. (2001). The laplace distribution and generalizations: A revisit with applications to communications, economics, engineering, and finance. Number 183. Birkhauser.
Examples
data(ais, package="sn")
attach(ais)
sexInd <- (sex=="female") + 0
x <- cbind(1,LBM,sexInd)
y <- BMI
tau <- 0.5
## EM.qr
EM.qr(y,x,tau)