Data Engineering and BI courses are free this week!
Function hidden_paths computes the most probable path of
hidden states of a (mixture) hidden Markov model given the observed sequences.
hidden_paths(model, respect_void = TRUE)The most probable paths of hidden states as an stslist object
(see seqdef). The log-probability is included as an attribute log_prob.
A hidden Markov model of class hmm or
a mixture HMM of class mhmm.
If TRUE (default), states at the time points
corresponding to TraMineR's void in the observed sequences are set to void
in the hidden state sequences as well.
hmm_biofam for information on the model used in the example;
and seqIplot, ssplot, or mssplot
for plotting hidden paths.
# Load a pre-defined HMM
data("hmm_biofam")
# Compute the most probable hidden state paths given the data and the model
mpp <- hidden_paths(hmm_biofam)
# Plot hidden paths for the first 100 individuals
ssplot(mpp, type = "I", tlim = 1:100)
# Because the model structure is so sparse that the posterior probabilities are
# mostly peaked to single state at each time point, the joint probability of
# observations and most probable paths of hidden states is almost identical to
# log-likelihood:
sum(attr(mpp, "log_prob"))
logLik(hmm_biofam)
Run the code above in your browser using DataLab