GaSP (version 1.0.6)

Visualize: Visualize a GaSPModel object.

Description

Carry out a functional analysis of variance (ANOVA) of a GaSPModel object and generate plotting coordinates for its estimated main and 2-input joint effects.

Usage

Visualize(GaSP_model, x_description, main_percent = 0, interaction_percent = 0)

Value

A list with the following elements:

anova_percent

A data frame containing the ANOVA percentages for all main effects and 2-input interaction effects.

main_effect

A data frame with plotting coordinates for the estimated main effects.

joint_effect

A data frame with plotting coordinates for the estimated 2-input joint effects.

total_percent

Total percentage of the prediction variation accounted for by all main effects and 2-input interaction effects.

average

Overall average of the prediction function, averaged with respect to all inputs.

SE_average

Standard error of the overall average.

Arguments

GaSP_model

Object of class GaSPModel.

x_description

A data frame describing the input variables. See DescribeX.

main_percent

An optional minimum percentage of variation explained by an input's main effect to return the effect's plotting coordinates; the default of zero gives plotting coordinates for all inputs.

interaction_percent

An optional minimum percentage of variation explained by the interaction effect of a pair of inputs to return the plotting coordinates for their joint effect (main effects plus interaction effect); the default of zero gives plotting coordinates for all pairs of inputs.

Details

If there are many inputs, to avoid excessive plotting of many trivial joint effects set interaction_percent = 1 say.

References

Schonlau, M. and Welch, W.J. (2006), "Screening the Input Variables to a Computer Model Via Analysis of Variance and Visualization", in Screening: Methods for Experimentation in Industry, Drug Discovery, and Genetics, Dean. A. and Lewis, S., eds., pp. 308-327, Springer, New York, doi:10.1007/0-387-28014-6_14.

Examples

# \dontshow{
x <- borehole$x
y <- borehole$y
theta <- c(
  5.767699e+01, 0.000000e+00, 0.000000e+00, 1.433571e-06,
  0.000000e+00, 2.366557e-06, 1.695619e-07, 2.454376e-09
)
alpha <- c(
  1.110223e-16, 0.000000e+00, 0.000000e+00, 0.000000e+00,
  0.000000e+00, 0.000000e+00, 2.494862e-03, 0.000000e+00
)
cor_par <- data.frame(Theta = theta, Alpha = alpha)
rownames(cor_par) <- colnames(borehole$x)
sp_var <- 38783.7
borehole_fit <- GaSPModel(
  x = borehole$x, y = borehole$y,
  reg_model = ~1, cor_family = "PowerExponential",
  cor_par = cor_par, random_error = FALSE,
  sp_var = sp_var
)
borehole_x_names <- colnames(borehole$x)
borehole_min <- c(0.05, 100.00, 63070.00, 990.00, 63.10, 700.00, 1120.00, 9855.00)
borehole_max <- c(0.15, 50000.00, 115600.00, 1110.00, 116.00, 820.00, 1680.00, 12045.00)
borehole_x_desc <- DescribeX(borehole_x_names, borehole_min, borehole_max)
# }
borehole_vis <- Visualize(borehole_fit, borehole_x_desc)