| misclass {simex} | R Documentation |
Takes a data.frame and produces misclassified data.
Probabilities for the missclassification are given in the mc.matrix.
misclass(data.org, mc.matrix, k)
data.org |
data.frame containing the factor variables. Must be
factors |
mc.matrix |
a list of matrices giving the probabilities for the
misclassification. Names of the list must correspond to the variable
names in data.org. The colnames must be named according to the
factor levels |
k |
the exponent for the misclassification matrix |
A data.frame containing the misclassified variables
Wolfgang Lederer, wolfgang.lederer@googlemail.com
mcsimex, build.mc.matrix,
diag.block
x1 <- factor(rbinom(100, 1, 0.5)) x2 <- factor(rbinom(100, 2, 0.5)) p1 <- matrix(c(1, 0, 0, 1), nrow = 2) p2 <- matrix(c(0.8, 0.1, 0.1, 0.1, 0.8, 0.1, 0.1, 0.1, 0.8), nrow = 3) colnames(p1) <- levels(x1) colnames(p2) <- levels(x2) x <- data.frame(x1 = x1, x2 = x2) mc.matrix <- list(x1 = p1, x2 = p2) x.mc <- misclass(data.org = x, mc.matrix = mc.matrix, k = 1) identical(x[, 1], x.mc[, 1]) # TRUE identical(x[, 2], x.mc[, 2]) # FALSE