| sb {sensitivity} | R Documentation |
sb implements the Sequential Bifurcations screening
method (Bettonvil and Kleijnen 1996). This is an alpha version
that might strongly evolve in the future.
sb(p, sign = rep("+", p), interaction = FALSE)
## S3 method for class 'sb':
ask(x, i = NULL, ...)
## S3 method for class 'sb':
tell(x, y, ...)
## S3 method for class 'sb':
print(x, ...)
## S3 method for class 'sb':
plot(x, ...)
p |
number of factors. |
sign |
a vector fo length p filled with "+" and
"-", giving the (assumed) signs of the factors effects. |
interaction |
a boolean, TRUE if the model is supposed to
be with interactions, FALSE otherwise. |
x |
a list of class "sb" storing the state of the
screening study at the current iteration. |
y |
a vector of model responses. |
i |
an integer, used to force a wanted bifurcation instead of that proposed by the algorithm. |
... |
not used. |
The model without interaction is
Y = beta_0 + sum_{i=1}^p beta_i X_i
while the model with interactions is
Y = beta_0 + sum_{i=1}^p beta_i X_i + sum_{1 <= i < j <= p} gamma_{ij} X_i X_j
In both cases, the factors are assumed to be uniformly distributed on [-1,1]. This is a difference with Bettonvil et al. where the factors vary across [0,1] in the former case, while [-1,1] in the latter.
Another difference with Bettonvil et al. is that in the current implementation, the groups are splitted right in the middle.
sb returns a list of class "sb", containing all
the input arguments detailed before, plus the following components:
i |
the vector of bifurcations. |
y |
the vector of observations. |
ym |
the vector of mirror observations (model with interactions only). |
The groups effects can be displayed with the print method.
B. Bettonvil and J. P. C. Kleijnen, 1996, Searching for important factors in simulation models with many factors: sequential bifurcations, European Journal of Operational Research, 96, 180–194.
# a model with interactions
p <- 50
beta <- numeric(length = p)
beta[1:5] <- runif(n = 5, min = 10, max = 50)
beta[6:p] <- runif(n = p - 5, min = 0, max = 0.3)
beta <- sample(beta)
gamma <- matrix(data = runif(n = p^2, min = 0, max = 0.1), nrow = p, ncol = p)
gamma[lower.tri(gamma, diag = TRUE)] <- 0
gamma[1,2] <- 5
gamma[5,9] <- 12
f <- function(x) { return(sum(x * beta) + (x %*% gamma %*% x))}
# 10 iterations of SB
sa <- sb(p, interaction = TRUE)
for (i in 1 : 10) {
x <- ask(sa)
y <- list()
for (i in names(x)) {
y[[i]] <- f(x[[i]])
}
tell(sa, y)
}
print(sa)
plot(sa)