SPOT (version 2.11.10)

buildLM: Linear Model Interface

Description

This is a simple wrapper for the lm function, which fits linear models. The purpose of this function is to provide an interface as required by SPOT, to enable modeling and model-based optimization with linear models. The linear model is build with main effects. Optionally, the model is also subject to the AIC-based stepwise algorithm, using the step function from the stats package.

Usage

buildLM(x, y, control = list())

Arguments

x

matrix of input parameters. Rows for each point, columns for each parameter.

y

one column matrix of observations to be modeled.

control

list of control parameters, currently only with parameters useStep and formula. The useStep boolean specifies whether the step function is used. The formula is passed to the lm function. Without a formula, a second order model will be built.

Value

an object of class "spotLinearModel", with a predict method and a print method.

Examples

# NOT RUN {
## Create design points
set.seed(1)
x <- cbind(runif(20)*15-5,runif(20)*15)
## Compute observations at design points (for Branin function)
y <- funBranin(x)
## Create model
fit <- buildLM(x,y)
## Print model parameters
print(fit)
## Predict at new location
predict(fit,cbind(1,2))
## True value at location
funBranin(cbind(1,2))
# }