QUALYPSOSS.ANOVA.step3: QUALYPSOSS.ANOVA.step3
In qualypsoss: Uncertainties of Climate Projections using Smoothing Splines

QUALYPSOSS.ANOVA.step3

R Documentation

QUALYPSOSS.ANOVA.step3

Description

SSANOVA decomposition of the ensemble of climate change responses using a Bayesian approach. In this second step, we infer deltaRV (variance of the residual errors) and phi (autocorrelation lag-1) considering hetero-autocorrelated residual errors, conditionally to smooth effects inferred in QUALYPSOSS.ANOVA.step1

Usage

QUALYPSOSS.ANOVA.step3(
  lOpt,
  lDim,
  yMCMC,
  RK,
  g.step1,
  lambda.step1,
  rho.step2,
  deltaRV.step2
)

Arguments

`lOpt`	list of options, returned by `QUALYPSOSS.check.option`
`lDim`	list of dimensions
`yMCMC`	array `nMCMC` x `nFull` of climate change responses
`RK`	large object containing the reproducing kernels, returned by `QUALYPSOSS.get.RK`
`g.step1`	smooth effect estimates provided by `QUALYPSOSS.ANOVA.step1`
`lambda.step1`	smooth parameter estimates provided by `QUALYPSOSS.ANOVA.step1`
`rho.step2`	lag-1 autocorrelation estimate provided by `QUALYPSOSS.ANOVA.step2`
`deltaRV.step2`	residual variance estimate provided by `QUALYPSOSS.ANOVA.step2`

Value

list containing diverse information aboutwith the following fields:

g.MCMC: Smooth effects g: array n x nFull x K where nFull is the number of possible combinations of predictors (discrete AND continuous),
g.hat: Smooth effects estimates: matrix nFull x K where nFull is the number of possible combinations of predictors (discrete AND continuous),
Schwarz: Schwarz criteria
BIC: BIC criteria