Simulate hidden Markov models
Simulate sequences of observed and hidden states given parameters of a hidden Markov model.
simulate_hmm(n_sequences, initial_probs, transition_probs, emission_probs, sequence_length)
n_sequences |
Number of simulations. |
initial_probs |
A vector of initial state probabilities. |
transition_probs |
A matrix of transition probabilities. |
emission_probs |
A matrix of emission probabilities or a list of such objects (one for each channel). |
sequence_length |
Length for simulated sequences. |
A list of state sequence objects of class stslist.
build_hmm and fit_model for building
and fitting hidden Markov models; ssplot for plotting
multiple sequence data sets; seqdef for more
information on state sequence objects; and simulate_mhmm
for simulating mixture hidden Markov models.
# Parameters for the HMM emission_probs <- matrix(c(0.5, 0.2, 0.5, 0.8), 2, 2) transition_probs <- matrix(c(5/6, 1/6, 1/6, 5/6), 2, 2) initial_probs <- c(1, 0) # Setting the seed for simulation set.seed(1) # Simulating sequences sim <- simulate_hmm( n_sequences = 10, initial_probs = initial_probs, transition_probs = transition_probs, emission_probs = emission_probs, sequence_length = 20) ssplot(sim, sortv = "mds.obs", type = "I")
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.