ident: Identifiability measures

In baccione-eawag/EawagSchoolTools: Miscellaneous Tools for Eawag Summer School in Environmental Systems Analysis

Description

Function to calculate identifiability measures.

Usage

ident(sen,delta.par=0,scale=0,max.subset.size=0)

Arguments

sen	matrix of model sensitivities (partial derivatives of model outcomes with respect to model parameters: dy/dpar); the columns of sen refer to different model parameters, the rows to different model outcomes
delta.par	model parameter uncertainty ranges (length equal to the number of columns of sen); if zero, then all ranges are assumed to be unity
scale	scaling factors of model results (if zero, then all scaling factors are assumed to be unity)
max.subset.size	parameter for maximum subset size

Details

This function calculates a parameter sensitivity ranking and collinearity indices for a series of parameter combinations based on linear sensitivity functions of a model, parameter uncertainty ranges and scale factors of model results.

The function is a simplified version of the program "ident" available at http://www.ident.eawag.ch.

Value

Returns a list containing: delta.msqr, collind.

Author(s)

Peter Reichert <[e-mail]>

baccione-eawag/EawagSchoolTools documentation built on Dec. 19, 2021, 6:38 a.m.