sobolTIIpf | R Documentation |
sobolTIIpf
implements the pick-freeze estimation of total interaction indices as described in Section 3.3 of Fruth et al. (2014). Total interaction indices (TII) are superset indices of pairs of variables, thus give the total influence of each second-order interaction. The pick-freeze estimation enables the strategy to reuse evaluations of Saltelli (2002). The total costs are (1+N) \times n
where N
is the number of indices to estimate. Via plotFG
, the TIIs can be visualized in a so-called FANOVA graph as described in section 2.2 of Muehlenstaedt et al. (2012).
sobolTIIpf(model = NULL, X1, X2, ...)
## S3 method for class 'sobolTIIpf'
tell(x, y = NULL, ...)
## S3 method for class 'sobolTIIpf'
print(x, ...)
## S3 method for class 'sobolTIIpf'
plot(x, ylim = NULL, ...)
## S3 method for class 'sobolTIIpf'
ggplot(data, mapping = aes(), ylim = NULL, ..., environment
= parent.frame())
## S3 method for class 'sobolTIIpf'
plotFG(x)
model |
a function, or a model with a |
X1 |
the first random sample. |
X2 |
the second random sample. |
x |
a list of class |
data |
a list of class |
y |
a vector of model responses. |
mapping |
Default list of aesthetic mappings to use for plot. If not specified, must be supplied in each layer added to the plot. |
environment |
[Deprecated] Used prior to tidy evaluation. |
... |
any other arguments for |
ylim |
optional, the y limits of the plot. |
sobolTIIpf
returns a list of class "sobolTIIpf"
, containing all
the input arguments detailed before, plus the following components:
call |
the matched call. |
X |
a |
y |
a vector of model responses. |
V |
the estimation of the overall variance. |
tii.unscaled |
the unscaled estimations of the TIIs together. |
tii.scaled |
the scaled estimations of the TIIs. |
Jana Fruth
J. Fruth, O. Roustant, S. Kuhnt, 2014, Total interaction index: A variance-based sensitivity index for second-order interaction screening, J. Stat. Plan. Inference, 147, 212–223.
A. Saltelli, 2002, Making best use of model evaluations to compute sensitivity indices, Comput. Phys. Commun., 145, 580-297.
T. Muehlenstaedt, O. Roustant, L. Carraro, S. Kuhnt, 2012, Data-driven Kriging models based on FANOVA-decomposition, Stat. Comput., 22 (3), 723–738.
sobolTIIlo
# Test case : the Ishigami function
# The method requires 2 samples
n <- 1000
X1 <- data.frame(matrix(runif(3 * n, -pi, pi), nrow = n))
X2 <- data.frame(matrix(runif(3 * n, -pi, pi), nrow = n))
# sensitivity analysis (the true values are 0, 0.244, 0)
x <- sobolTIIpf(model = ishigami.fun, X1 = X1, X2 = X2)
print(x)
# plot of tiis and FANOVA graph
plot(x)
library(ggplot2)
ggplot(x)
library(igraph)
plotFG(x)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.