residuals.seqModel: Extract residuals from a sequence of regression models

Description

Extract residuals from a sequence of regression models, such as submodels along a robust or groupwise least angle regression sequence, or sparse least trimmed squares regression models for a grid of values for the penalty parameter.

Usage

# S3 method for seqModel
residuals(object, s = NA, standardized = FALSE, drop = !is.null(s), ...)
# S3 method for tslars
residuals(object, p, ...)
# S3 method for perrySeqModel
residuals(object, ...)
# S3 method for sparseLTS
residuals(
  object,
  s = NA,
  fit = c("reweighted", "raw", "both"),
  standardized = FALSE,
  drop = !is.null(s),
  ...
)

Value

A numeric vector or matrix containing the requested residuals.

Arguments

object: the model fit from which to extract residuals.
s: for the "seqModel" method, an integer vector giving the steps of the submodels for which to extract the residuals (the default is to use the optimal submodel). For the "sparseLTS" method, an integer vector giving the indices of the models for which to extract residuals. If fit is "both", this can be a list with two components, with the first component giving the indices of the reweighted fits and the second the indices of the raw fits. The default is to use the optimal model for each of the requested estimators. Note that the optimal models may not correspond to the same value of the penalty parameter for the reweighted and the raw estimator.
standardized: a logical indicating whether the residuals should be standardized (the default is FALSE). Note that this argument is deprecated and may be removed as soon as the next version. Use rstandard instead to extract standardized residuals.
drop: a logical indicating whether to reduce the dimension to a vector in case of only one step.
...: for the "tslars" method, additional arguments to be passed down to the "seqModel" method. For the other methods, additional arguments are currently ignored.
p: an integer giving the lag length for which to extract residuals (the default is to use the optimal lag length).
fit: a character string specifying which residuals to extract. Possible values are "reweighted" (the default) for the residuals from the reweighted estimator, "raw" for the residuals from the raw estimator, or "both" for the residuals from both estimators.

Author

Andreas Alfons

Examples

Run this code

## generate data
# example is not high-dimensional to keep computation time low
library("mvtnorm")
set.seed(1234)  # for reproducibility
n <- 100  # number of observations
p <- 25   # number of variables
beta <- rep.int(c(1, 0), c(5, p-5))  # coefficients
sigma <- 0.5      # controls signal-to-noise ratio
epsilon <- 0.1    # contamination level
Sigma <- 0.5^t(sapply(1:p, function(i, j) abs(i-j), 1:p))
x <- rmvnorm(n, sigma=Sigma)    # predictor matrix
e <- rnorm(n)                   # error terms
i <- 1:ceiling(epsilon*n)       # observations to be contaminated
e[i] <- e[i] + 5                # vertical outliers
y <- c(x %*% beta + sigma * e)  # response
x[i,] <- x[i,] + 5              # bad leverage points


## robust LARS
# fit model
fitRlars <- rlars(x, y, sMax = 10)
# extract residuals
residuals(fitRlars)
head(residuals(fitRlars, s = 1:5))


## sparse LTS over a grid of values for lambda
# fit model
frac <- seq(0.2, 0.05, by = -0.05)
fitSparseLTS <- sparseLTS(x, y, lambda = frac, mode = "fraction")
# extract residuals
residuals(fitSparseLTS)
head(residuals(fitSparseLTS, fit = "both"))
head(residuals(fitSparseLTS, s = NULL))
head(residuals(fitSparseLTS, fit = "both", s = NULL))