rsig.all: Robust Signature Selection for Survival Outcomes with...

In rsig: Robust Signature Selection for Survival Outcomes

Description

Fit a specified model using subsamples and evaluate its performance on out-of-subsample data.

Usage

  rsig.all(surv, X, model, n.rep.out = 10L, n.rep.in = 10L,
    plapply = mclapply, sd.filter = NULL)

Arguments

surv	[Surv] Survival object, see Surv.
X	[data.frame] Data frame or matrix or matrix of input data (rows: examples, columns: features).
model	[character(1)] Model to use. One of "rs.prlasso" (preconditioned lasso with robust selection), "rs.lasso" (penalized Cox regression with robust selection), "prlasso" (preconditioned lasso), or "lasso" (penalized Cox regression)
n.rep.out	[integer] The number of replicates to be used to estimate selection probability of features (outer subsampling)
n.rep.in	[integer] The number of replicates to be used for model aggregation (inner subsampling)
plapply	[function] Function used for internal parallelization. Default is mclapply for multi-core parallel execution.
sd.filter	[list] Pre-filter features by their standard deviation, by one of the options specified: topk: no. of features to be selected with largest standard devations. quant: the min percentile in standard deviations of features to be selected.

Value

Object of class “list”.

selection.frequency	a named vector of selected features with their estimated selection frequencies amongst n.rep.out replicates.
perf	performance measured on out-of-sample data in n.rep.out replicates

See Also

rsig

rsig documentation built on May 30, 2017, 7:57 a.m.