polynomial.model.lsd: Fit a polynomial meta-model to a LSD model sample data

Description

This function fits a Polynomial meta-model of first or second order, with or without interactions, to the sampled data from a LSD simulation model. Polynomial meta-models are usually inadequate to fit nonlinear simulation models, please use the estimated meta-model carefully.

Usage

polynomial.model.lsd( data, ext.wgth = 0.5, ols.sig = 0.2,
                      orderModel = 0, interactModel = 0, digits = 4 )

Value

The function returns an object/list of class polynomial-model containing several items:

selected: an object containing the selected estimated meta-model.
comparison: a print-ready table with all fitting statistics for all fitted meta-model specifications.
R2: the adjusted R2 in-sample fitting statistic for the selected meta-model.
rmse: the RMSE out-of-sample fitting statistic for the selected meta-model.
mae: the MAE out-of-sample fitting statistic for the selected meta-model.
rma: the RMA out-of-sample fitting statistic for the selected meta-model.
extN: number of out-of-sample observations.
estimation: a print-ready table with the coefficients (hyper-parameters) of the selected estimated meta-model.
estimation.std: a print-ready table with the standardized coefficients (hyper-parameters) of the selected estimated meta-model.
coefficients: a vector with the coefficients (hyper-parameters) of the selected estimated meta-model.
coefficients.std: a vector with the standardized coefficients (hyper-parameters) of the selected estimated meta-model.
order: order of the selected polynomial model.
polyNames: name of the selected polynomial model.
interact: number of the selected interaction mode.
interactNames: name of the selected interaction mode.

Arguments

data: an object created by a previous call to read.doe.lsd which contains all the required experimental data for the analysis.
ext.wgth: numeric in [0, 1]: the weight given to the fitting metrics calculated over the out-of-sample (external) validation sample in regard to the in-sample metrics. The default value is 0.5.
ols.sig: numeric in [0, 1]: the minimum significance considered in the OLS regression.
orderModel: a number corresponding to the polynomial model order: 0 = automatic selection (according to fitting metrics, the default); 1 = first order; 2 = second order.
interactModel: a number indicating the presence of interaction terms in the model: 0 = automatic selection (according to fitting metrics, the default); 1 = no , 2 = yes.
digits: integer: the number of significant digits to show in results. The default is 4.

Author

tools:::Rd_package_author("LSDsensitivity")

Details

This function fits a polynomial meta-model to the experimental data set previously loaded with read.doe.lsd using the ordinary least-squares (OLS) method.

This function is a wrapper to the function lm in stats-package.

Examples

Run this code

# 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,
#    preferrably using two sets of sampled data (DoEs), one for model
#    estimation and the other for out-of-sample (external) validation
# 3. fit the polynomial meta-model using polynomial.model.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 <- polynomial.model.lsd( dataSet )       # estimate best polynomial meta-model
                                               # using defaults (auto model selection)

print( model$comparison )                      # model comparison table
print( model$estimation.std )                  # model estimation (standardized) table

Run the code above in your browser using DataLab