delsa: Distributed Evaluation of Local Sensitivity Analysis

Description

delsa implements Distributed Evaluation of Local Sensitivity Analysis to calculate first order parameter sensitivity at multiple locations in parameter space. The locations in parameter space can either be obtained by a call to parameterSets or by specifying X0 directly, in which case the prior variance of each parameter varprior also needs to be specified. Via plot (which uses functions of the package ggplot2 and reshape2), the indices can be visualized.

Usage

delsa(model = NULL, perturb=1.01,
  par.ranges, samples, method,
  X0, varprior, varoutput,
  ...)
  
# S3 method for delsa
tell(x, y = NULL,...)
# S3 method for delsa
print(x, ...)
# S3 method for delsa
plot(x, which=1:3, ask = dev.interactive(), ...)

Value

delsa returns a list of class "delsa", 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: a vector of model responses.
delsafirst: the first order indices for each location in X0.
deriv: the values of derivatives for each location in X0

Arguments

model: a function, or a model with a predict method, defining the model to analyze.
perturb: Perturbation used to calculate sensitivity at each evaluation location
par.ranges: A named list of minimum and maximum parameter values
samples: Number of samples to generate. For the "grid" and "innergrid" method, corresponds to the number of samples for each parameter, and may be a vector.
method: Sampling scheme. See parameterSets
X0: Parameter values at which to evaluate sensitivity indices. Can be used instead of specifying sampling method
varprior: Prior variance. If X0 is specified, varprior must also be specified.
varoutput: Output variance. If "summation" is specified (default value), the ouput variance is computed by summing the first order effects. If "empirical" is specified, the ouput variance is estimated frome the output sample.
...: any other arguments for model which are passed unchanged each time it is called.
x: a list of class "delsa" storing the state of the sensitivity study (parameters, data, estimates).
y: a vector of model responses.
which: if a subset of the plots is required, specify a subset of the numbers 1:3
ask: logical; if TRUE, the user is asked before each plot, see par(ask=.)

Author

Conversion for sensitivity package by Joseph Guillaume, based on original R code by Oldrich Rakovec. Addition of the varoutput argument by Bertrand Iooss (2020).

Details

print shows summary of the first order indices across parameter space.

plot shows: (1) the cumulative distribution function of first order sensitivity across parameter space, (2) variation of first order sensitivity in relation to model response, and (3) sensitivity in relation to parameter value.

References

Rakovec, O., M. C. Hill, M. P. Clark, A. H. Weerts, A. J. Teuling, R. Uijlenhoet (2014), Distributed Evaluation of Local Sensitivity Analysis (DELSA), with application to hydrologic models, Water Resour. Res., 50, 1-18

Examples

Run this code

# Test case : the non-monotonic Sobol g-function
# (there are 8 factors, all following the uniform distribution on [0,1])

# \donttest{
library(randtoolbox)
x <- delsa(model=sobol.fun,
           par.ranges=replicate(8,c(0,1),simplify=FALSE),
           samples=100,method="sobol")

# Summary of sensitivity indices of each parameter across parameter space
print(x)

library(ggplot2)
library(reshape2)
plot(x)
# }

Run the code above in your browser using DataLab

Get 50% off unlimited learning