transitionScale {VanillaICE}R Documentation

Scales the transition probabilities of the hidden Markov model

Description

Accessor and replacement methods for scaling the transition probabilities

Usage

transitionScale(object)
transitionScale(object) <- value

Arguments

object An object of class HmmParameter
value

{A matrix of dimension STATES x STATES, where STATES is the number of hidden states.}

Details

The probability of remaining in the same state, $P(S_t = S_{t+1})$ (the diagonal of the transition probability matrix) is a function of the distance between SNPs. The probability of transitioning to some other state is epsilon, where epsilon = 1 - $P(S_t = S_{t+1})$. The epsilon is split among STATES-1 states. By default, the probability of transitioning from an altered state back to the normal state is twice as likely as the probability of transitioning between two altered states. The weights for epsilon are provided in the transitionScale matrix in objects of class HmmParameter.

Value

A matrix

Author(s)

R. Scharpf

See Also

scaleTransitionProbability


[Package VanillaICE version 1.4.0 Index]