superBca: Fast combination of multiple simple support functions

In RAPLER/dst-1: Using the Theory of Belief Functions

Fast combination of multiple simple support functions

Description

Fast combination of multiple simple support functions

Usage

superBca(x, y, a, y0 = 0, flip = TRUE, tree_type = "single")

Arguments

x	A binary matrix of simple support functions define on a same frame of discernment (Fod).
y	A column matrix y of TRUE/FALSE values.
a	The mass value allotted to each simple support function. All support functions have the same mass.
y0	A value used to check which rows of the matrix x are to be inverted. Set at 0 (FALSE).
flip	Parameter used when some rows of the table x need to be reversed. The default value is TRUE (check rows).

Details

This function handles the case of combining several simple support functions defined on a very large frame of discernment (Fod). The simple support functions are arranged row by row in a binary array x. The number of rows of the array is equal to the number of support functions to be combined.The support functions can be defined as is or by their complement when it's faster to code. A column matrix y of TRUE/FALSE values is used to identify the rows of the array that need to be inverted.

Value

z An object of class bcaspec called a bca for "basic chance assignment"

Author(s)

Peiyuan Zhu

Examples

x1 <- bca(tt= matrix(c(1,0,1,1),nrow = 2, byrow = TRUE), 
   m = c(0.9,0.1), cnames = c("yes", "no"),
   varnames = "x", idvar = 1)
x2 <- bca(tt = matrix(c(0,1,1,1),nrow = 2, byrow = TRUE),
   m = c(0.9,0.1), cnames = c("yes", "no"), 
   varnames = "x", idvar = 1)
x <- rbind(x1$tt[1,], x2$tt[1,])
rownames(x) <- nameRows(x)
y <- matrix(c(TRUE, TRUE), ncol = 1 )
a <- 0.9
z <- superBca(x, y, a, tree_type="single")

RAPLER/dst-1 documentation built on June 2, 2025, 9:22 a.m.