mboost (version 2.2-3)

stabsel: Stability Selection

Description

Selection of influential variables or model components with error control.

Usage

stabsel(object, FWER = 0.05, cutoff, q,
        folds = cv(model.weights(object), type = "subsampling", B = 100),
        papply = mclapply, verbose = TRUE, ...)

Arguments

object

an mboost object.

FWER

family-wise error rate to be controlled by the selection procedure.

cutoff

cutoff between 0.5 and 1.

q

average number of selected base-learners.

folds

a weight matrix with number of rows equal to the number of observations, see cvrisk.

papply

(parallel) apply function, defaults to mclapply. Alternatively, parLapply can be used. In the latter case, usually more setup is needed (see example for some details).

verbose

logical (default: TRUE) that determines wether warnings should be issued.

...

additional arguments to cvrisk.

Value

• An object of class stabsel with elements
• phat
  selection probabilities.
• selected
  elements with maximal selection probability greater cutoff.
• max
  maximum of selection probabilities.
• cutoff
  cutoff used.
• q
  average number of selected variables used.
• FWER
  family-wise error rate.

Details

This function implements the "stability selection" procedure by Meinshausen and Buehlmann (2010).

Either cutoff or q must be specified. The probability of selecting at least one non-influential variable (or model component) is less than FWER.

References

N. Meinshausen and P. Buehlmann (2010), Stability selection. Journal of the Royal Statistical Society, Series B, 72(4).

Examples

data(bodyfat)

  ### (too) low-dimensional example
  mod <- glmboost(DEXfat ~ ., data = bodyfat)
  (sbody <- stabsel(mod, q = 3,
                    folds = cv(model.weights(mod), type = "subsampling", B = 25)))
  opar <- par(mai = par("mai") * c(1, 1, 1, 2.7))
  plot(sbody)
  par(opar)