model.pred.lsd {LSDsensitivity}

Predict meta-model response at given point(s)

Description

This function predicts the meta-model response at a specific point(s) in the factor (parameter) space and provides a confidence interval for the prediction(s) at 95% confidence.

Usage

model.pred.lsd( data.point, model )

Arguments

data.point

a single or multi line data frame which contains values (in the rows) for all the meta-model factors/variables (in the columns).

model

an object created by a previous call to kriging.model.lsd or polynomial.model.lsd which contains the meta-model estimated hyper-parameters.

Details

This function simply evaluate the meta-model value at the given point. All factor values must be specified. data.point can also be specified as an ordered vector or matrix, following the same order for the factors as defined in the meta-model specification.

This function is a wrapper to the functions predict.km in DiceKriging-package and predict.lm in stats-package.

Value

The function returns a list containing the prediction(s) and the confidence bounds. If data.point is a data frame or matrix with more than one line, the list elements are vectors. The list element names are:

mean

the expected response value.

lower

the lower confidence bound.

upper

the upper confidence bound.

Author(s)

NA

See Also

kriging.model.lsd(), polynomial.model.lsd()

predict.km in DiceKriging-package, predict.lm in stats-package

Examples

# get the example directory name
path <- system.file( "extdata/sobol", package = "LSDsensitivity" )

# Steps to use this function:
# 1. define the variables you want to use in the analysis
# 2. load data from a LSD simulation saved results using read.doe.lsd
# 3. fit a Kriging (or polynomial) meta-model using kriging.model.lsd
# 4. estimate the meta-model response at any set of points applying
#    model.pred.lsd

lsdVars <- c( "var1", "var2", "var3" )         # the definition of existing variables

dataSet <- read.doe.lsd( path,                 # data files folder
                         "Sim3",               # data files base name (same as .lsd file)
                         "var3",               # variable name to perform the sensitivity analysis
                         does = 2,             # number of experiments (data + external validation)
                         saveVars = lsdVars )  # LSD variables to keep in dataset

model <- kriging.model.lsd( dataSet )          # estimate best Kriging meta-model

# creates a set of four random points in parameter space
points <- data.frame( par1 = rnorm( 4 ), par2 = rnorm( 4 ), par3 = rnorm( 4 ) )

response <- model.pred.lsd( points, model )    # predict model response at the 3 points

print( points )
print( response )