pW-Criteria: Identification criteria allow estimating the relative degree...

In dazamora/IDFtool: Estimation Intensity-Duration-Frequency Curves for Rainfall Series

Identification criteria allow estimating the relative degree of likelihood of each model by means of their posterior weights (for AIC and AICc) or posterior model probability (for BIC and KIC)

Description

This function determine what probability distribution function has the best goodness-of-fit to observations, number of parameters and the quality of taking in account different information criterias that are evaluated in the criteria proposed by (Siena et al., 2017).

Usage

p.criteria(metrics, critnames, pdfnames)

Arguments

metrics	a numeric matrix with the values of criterias AIC, BIC, AICc and KIC (rows) evaluated by each PDFs (columns).
critnames	a character vector with the names of information criteria evaluated.
pdfnames	a character vector with the names of PDFs evaluated.

Value

Provided a matrix with values of pW criteria by each PDFs and information criterias.

Author(s)

Adriana Pina <[e-mail]> and David Zamora <[e-mail]> Water Resources Engineering Research Group - GIREH

References

Siena, M., Riva, M., Giamberini, M., & Gouze, P. (2017). Statistical modeling of gas-permeability spatial variability along a limestone core. Spatial Statistics. https://doi.org/10.1016/j.spasta.2017.07.007

Examples

# Example of five PDFs and their respectives values of four information criterias.
data(fractures.crit)

pW.1 <- p.criteria(metrics = fractures.crit, critnames = rownames(fractures.crit), 
                   pdfnames = colnames(fractures.crit))
pW.1
# GEV: AIC= 100, BIC= 100, AICc= 1, KIC= 99 

dazamora/IDFtool documentation built on Jan. 1, 2023, 3:29 p.m.