Mqrcm-package {Mqrcm} | R Documentation |
M-Quantile Regression Coefficients Modeling
Description
This package implements Frumento and Salvati (2020) method for M-quantile regression coefficients modeling (Mqrcm), in which M-quantile regression coefficients are described by (flexible) parametric functions of the order of the quantile. This permits modeling the entire conditional M-quantile function of a response variable.
Details
Package: | Mqrcm |
Type: | Package |
Version: | 1.3 |
Date: | 2024-02-12 |
License: | GPL-2 |
The function iMqr
permits specifying the regression model.
Two special functions, slp
and plf
, are provided to facilitate model building.
The auxiliary functions summary.iMqr
, predict.iMqr
, and plot.iMqr
can be used to extract information from the fitted model.
Author(s)
Paolo Frumento
Maintainer: Paolo Frumento <paolo.frumento@unipi.it>
References
Frumento, P., Salvati, N. (2020). Parametric modeling of M-quantile regression coefficient functions with application to small area estimation, Journal of the Royal Statistical Society, Series A, 183(1), p. 229-250.
Examples
# use simulated data
n <- 250
x <- rexp(n)
y <- runif(n, 0, 1 + x)
model <- iMqr(y ~ x, formula.p = ~ p + I(p^2))
summary(model)
summary(model, p = c(0.1,0.2,0.3))
predict(model, type = "beta", p = c(0.1,0.2,0.3))
predict(model, type = "CDF", newdata = data.frame(x = c(1,2,3), y = c(0.5,1,2)))
predict(model, type = "QF", p = c(0.1,0.2,0.3), newdata = data.frame(x = c(1,2,3)))
predict(model, type = "sim", newdata = data.frame(x = c(1,2,3)))
par(mfrow = c(1,2)); plot(model, ask = FALSE)