sensitivity (version 1.10.1)

sobolowen: Monte Carlo Estimation of Sobol' Indices (improved formulas of Owen (2013)

Description

sobolowen implements the Monte Carlo estimation of the Sobol' indices for both first-order and total indices at the same time (alltogether $2p$ indices). Take as input 3 independent matrices. These are called the Owen estimators.

Usage

sobolowen(model = NULL, X1, X2, X3, nboot = 0, conf = 0.95, varest = 2, ...)
## S3 method for class 'sobolowen':
tell(x, y = NULL, return.var = NULL, varest = 2, \dots)
## S3 method for class 'sobolowen':
print(x, \dots)
## S3 method for class 'sobolowen':
plot(x, ylim = c(0, 1), ...)

Arguments

model

a function, or a model with a predict method, defining the model to analyze.

X1

the first random sample.

X2

the second random sample.

X3

the third random sample.

nboot

the number of bootstrap replicates.

conf

the confidence level for bootstrap confidence intervals.

varest

choice for the variance estimator for the denominator of the Sobol' indices. varest=1 is for a classical estimator. varest=2 (default) is for the estimator proposed in Janon et al. (2012).

x

a list of class "sobol" storing the state of the sensitivity study (parameters, data, estimates).

y

a vector of model responses.

return.var

a vector of character strings giving further internal variables names to store in the output object x.

ylim

y-coordinate plotting limits.

...

any other arguments for model which are passed unchanged each time it is called

Value

• sobolowen returns a list of class "sobolowen", containing all the input arguments detailed before, plus the following components:
• call
  the matched call.
• X
  a data.frame containing the design of experiments.
• y
  the response used
• V
  the estimations of Variances of the Conditional Expectations (VCE) with respect to each factor and also with respect to the complementary set of each factor ("all but $X_i$").
• S
  the estimations of the Sobol' first-order indices.
• T
  the estimations of the Sobol' total sensitivity indices.
• Users can ask more ouput variables with the argument return.var (for example, bootstrap outputs V.boot, S.boot and T.boot).

References

A. Owen, 2013, Better estimations of small Sobol' sensitivity indices, ACM Transactions on Modeling and Computer Simulations (TOMACS), 23(2), 11. Janon, A., Klein T., Lagnoux A., Nodet M., Prieur C. (2012), Asymptotic normality and efficiency of two Sobol index estimators. Accepted in ESAIM: Probability and Statistics.

See Also

sobol, sobol2002, sobol2007, soboljansen, sobolEff, sobolmara, sobolGP

Examples

# Test case : the non-monotonic Sobol g-function

# The method of sobolowen requires 3 samples
# There are 8 factors, all following the uniform distribution
# on [0,1]

library(boot)
n <- 1000
X1 <- data.frame(matrix(runif(8 * n), nrow = n))
X2 <- data.frame(matrix(runif(8 * n), nrow = n))
X3 <- data.frame(matrix(runif(8 * n), nrow = n))

# sensitivity analysis

x <- sobolowen(model = sobol.fun, X1, X2, X3, nboot = 100)
print(x)
plot(x)