Visualize the spectral condition number against the regularization parameter

This function is now deprecated. Please use CNplot instead.

conditionNumberPlot(
  S,
  lambdaMin,
  lambdaMax,
  step,
  type = "Alt",
  target = default.target(S),
  norm = "2",
  digitLoss = FALSE,
  rlDist = FALSE,
  vertical = FALSE,
  value,
  main = TRUE,
  nOutput = FALSE,
  verbose = TRUE
)

Arguments

S: Sample covariance matrix.
lambdaMin: A numeric giving the minimum value for the penalty parameter.
lambdaMax: A numeric giving the maximum value for the penalty parameter.
step: An integer determining the number of steps in moving through the grid [lambdaMin, lambdaMax].
type: A character indicating the type of ridge estimator to be used. Must be one of: "Alt", "ArchI", "ArchII".
target: A target matrix (in precision terms) for Type I ridge estimators.
norm: A character indicating the norm under which the condition number is to be calculated/estimated. Must be one of: "1", "2".
digitLoss: A logical indicating if the approximate loss in digits of accuracy should also be visualized in the output graph.
rlDist: A logical indicating if the relative distance to the set of singular matrices should also be visualized in the output graph.
vertical: A logical indicating if output graph should come with a vertical line at a pre-specified value for the penalty parameter.
value: A numeric indicating a pre-specified value for the penalty parameter.
main: A logical indicating if output graph should contain type of estimator as main title.
nOutput: A logical indicating if numeric output should be returned.
verbose: A logical indicating if information on progress should be printed on screen.

Value

The function returns a graph. If nOutput = TRUE the function also returns an object of class list:

lambdas: A numeric vector representing all values of the penalty parameter for which the condition number was calculated.
conditionNumbers: A numeric vector containing the condition number for each value of the penalty parameter given in lambdas.

Details

See CNplot.

Author

Carel F.W. Peeters <carel.peeters@wur.nl>

Examples


## Obtain some (high-dimensional) data
p = 25
n = 10
set.seed(333)
X = matrix(rnorm(n*p), nrow = n, ncol = p)
colnames(X)[1:25] = letters[1:25]
Cx <- covML(X)

## Assess spectral condition number across grid of penalty parameter
conditionNumberPlot(Cx, lambdaMin = .0001, lambdaMax = 50, step = 1000)
#> Perform input checks... 
#> Calculating spectral condition numbers... 
#> Plotting...