InitialLawMk: Estimation of the initial law (Markov model)

In SMM: Simulation and Estimation of Multi-State Discrete-Time Semi-Markov and Markov Models

Description

For order 1, estimation of initial law by computing the stationary law of the Markov chain.

For order greater than 1, estimation of initial law by computing the state frequencies.

Usage

InitialLawMk(E, seq, Ptrans, k)

Arguments

E	Vector of state space
seq	List of sequence(s)
Ptrans	Matrix of transition probabilities of size (S^(k))xS, with S = length(E)
k	Order of the Markov chain

Value

init	Vector of the initial law

Author(s)

Vlad Stefan Barbu, [e-mail]
Caroline Berard, [e-mail]
Dominique Cellier, [e-mail]
Mathilde Sautreuil, [e-mail]
Nicolas Vergne, [e-mail]

See Also

InitialLawMk, estimSM, simulSM, estimMk, simulMk

Examples

seq = list(c("a","c","c","g","t","a","a","a","a","g","c","t","t","t","g"))
res = estimMk(seq = seq, E = c("a","c","g","t"), k = 1)
p = res$Ptrans

InitialLawMk(E = c("a","c","g","t"), seq = seq, Ptrans = p, k = 1)

Example output

Loading required package: seqinr
Loading required package: DiscreteWeibull
Loading required package: Rsolnp
Warning message:
In estimMk(seq = seq, E = c("a", "c", "g", "t"), k = 1) :
  missing transitions
$init
[1] 0.2205882 0.2205882 0.2058824 0.3529412

SMM documentation built on Jan. 31, 2020, 5:07 p.m.