confusion: Misclassification probabilities in mixtures
Description
Estimates a misclassification probability in a mixture distribution
between two mixture components from estimated posterior probabilities
regardless of component parameters, see Hennig (2010).
Usage
confusion(z,pro,i,j,adjustprobs=FALSE)
Value
Estimated probability that an observation generated by component
j is classified to component i by maximum a posteriori rule.
Arguments
z
matrix of posterior probabilities for observations (rows) to
belong to mixture components (columns), so entries need to sum up to
1 for each row.
pro
vector of component proportions, need to sum up to 1.
i
integer. Component number.
j
integer. Component number.
adjustprobs
logical. If TRUE, probabilities are
initially standardised so that those for components i and
j add up to one (i.e., if they were the only components).
set.seed(12345)
m <- rpois(20,lambda=5)
dim(m) <- c(5,4)
pro <- apply(m,2,sum)
pro <- pro/sum(pro)
m <- m/apply(m,1,sum)
round(confusion(m,pro,1,2),digits=2)