Container of the results of PCE sensitivity indexes computation.
Objects from this class are created by calls to function
matrix with as many rows as inputs and 3 columns. Values of the PCE sensitivity indexes. The row labels are the inputs numbers. The column labels are LE, PE, TPE.
indexes[i, "LE"] is the Linear Effect of the input
indexes[i, "PE"] is the Polynomial Effect
(called "SU" in Sudret, 2008). It is the effect of the
monomials in which only the input
indexes[i, "TPE"] is the Total Polynomial Effect
(often called "SUT"). It is the effect of all the
monomials in which the input
Percentages of the PCE sensitivity indexes, i.e
indexes expressed as percentages
of the sums of their columns.
vector of length 2. The values of R2 and RMSEP (RMSEP: Root Mean Square Error Prediction).
vector of length equal to the number of monomials. Individual monomial sensitivity indexes.
vector of length equal to the number of monomials plus one. Regression coefficients. The first one is the constant term.
vector of length equal to the number of rows of the dataset. Metamodel outputs.
object of class
coding the polynomial structure.
expression of class ‘call’. The command
which creates the
used as input in the creator command.
signature(object = "PCEfit"): display the names, class and
length of all the components. See the description
of the generic function
signature(object = "PCEfit", all=FALSE, ...):
method of function
all is set to FALSE (the default),
only the components
fit are printed.
The additional arguments are passed to the
signature(object = "PCEfit"): same as
Global sensitivity analysis using polynomial chaos expansions. Bruno Sudret. In Reliability Engineering and System Safety, Vol. 93, Issue 7, July 2008, pages 964-979.
PCESI, creator of objects from this class.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.