sivipboot: Confidence Intervals for the Total Sensitivity Indices by...

In sivipm: Sensitivity Indices with Dependent Inputs

Description

Confidence intervals for the total sensitivity indices by a bootstrap method.

Usage

sivipboot(Y, XIndic, B, nc=2, graph=FALSE, alea=FALSE,
                  fast=FALSE, alpha=0.05)

Arguments

Y	Outputs. A data.frame with as many rows as observations and as many columns as response variables.
XIndic	Object of class polyX which contains the polynomial description and the dataset of inputs.
B	Number of bootstrap replicates.
nc	Number of components.
graph	If TRUE, boxplot display.
alea	If TRUE, an uniform random variable is included in the analysis (see sivipm).
fast	If TRUE, auxiliary results are calculated from the Miller's formulae more adapted to big datasets.
alpha	Level of the bootstrap confidence intervals.

Value

A matrix with as many rows as input variables and two columns: the lower and upper bounds of the total sensitivity indices percentile bootstrap confidence intervals.

See Also

sivipm

Examples

X <- cornell0[,1:3] # X-inputs
Y <- as.data.frame( cornell0[,8]) # response variable
# Creation of the polynomial:
P <- vect2polyX(X, c("1", "2", "3", "3*3*3"))
set.seed(15) #alea seed
nloops <- 3 # number of loops, example for fast running
nc <- 2 # number of components
sivipboot(Y, P, nloops, nc, fast=TRUE)

sivipm documentation built on May 2, 2019, 6:41 a.m.