residuals {ARCensReg} R Documentation

## Extract model residuals from ARpCRM or ARtpCRM objects

### Description

The conditional residuals are obtained by subtracting the fitted values from the response vector, while the quantile residuals are obtained by inverting the estimated distribution function for each observation to obtain approximately normally distributed residuals. See, for instance, Dunn and Smyth (1996) and Kalliovirta (2012).

### Usage

## S3 method for class 'ARpCRM'
residuals(object, ...)

## S3 method for class 'ARtpCRM'
residuals(object, ...)


### Arguments

 object An object inheriting from class ARpCRM or ARtpCRM, representing a fitted AR(p) censored linear model. ... Further arguments passed to or from other methods.

### Value

An object of class "residARpCRM", with the following components:

 residuals Vector with the conditional residuals of length n. quantile.resid Vector with the quantile residuals of length n.

Generic function plot has methods to show a graphic of residual vs. time, an autocorrelation plot, a histogram, and Quantile-Quantile (Q-Q) plot for the quantile residuals.

### Author(s)

Fernanda L. Schumacher, Katherine L. Valeriano, Victor H. Lachos, Christian E. Galarza, and Larissa A. Matos

### References

Dunn PK, Smyth GK (1996). “Randomized quantile residuals.” Journal of Computational and Graphical Statistics, 5(3), 236–244.

Kalliovirta L (2012). “Misspecification tests based on quantile residuals.” The Econometrics Journal, 15(2), 358–393.

ARCensReg, ARtCensReg

### Examples


## Example 1: Generating data with normal innovations
set.seed(93899)
x = cbind(1, runif(300))
dat1 = rARCens(n=300, beta=c(1,-1), phi=c(.48,-.2), sig2=.5, x=x,
cens='left', pcens=.05, innov="norm")

# Fitting the model with normal innovations
mod1 = ARCensReg(dat1$data$cc, dat1$data$lcl, dat1$data$ucl, dat1$data$y,
x, p=2, tol=0.001)
mod1$tab plot(residuals(mod1)) # Fitting the model with Student-t innovations mod2 = ARtCensReg(dat1$data$cc, dat1$data$lcl, dat1$data$ucl, dat1$data$y, x, p=2, tol=0.001) mod2$tab
plot(residuals(mod2))

## Example 2: Generating heavy-tailed data
set.seed(12341)
x = cbind(1, runif(300))
dat2 = rARCens(n=300, beta=c(1,-1), phi=c(.48,-.2), sig2=.5, x=x,
cens='left', pcens=.05, innov="t", nu=3)

# Fitting the model with normal innovations
mod3 = ARCensReg(dat2$data$cc, dat2$data$lcl, dat2$data$ucl, dat2$data$y,
x, p=2, tol=0.001)
mod3$tab plot(residuals(mod3)) # Fitting the model with Student-t innovations mod4 = ARtCensReg(dat2$data$cc, dat2$data$lcl, dat2$data$ucl, dat2$data$y, x, p=2, tol=0.001) mod4$tab
plot(residuals(mod4))


[Package ARCensReg version 3.0.1 Index]