global_decode function

Global decoding of HMM

Computes sequence of state predictions for each individual

global_decode(object, ddl = NULL, state.names = NULL)

Arguments

• object: fitted crm model (must be an HMM model)
• ddl: design data list; will be computed if NULL
• state.names: names for states used to label output; if NULL uses strata.labels + Dead state

Returns

matrix of state predictions

Examples

#

# This example is excluded from testing to reduce package check time
# cormack-jolly-seber model
data(dipper)
mod=crm(dipper,model="hmmcjs")
global_decode(mod)

References

Zucchini, W. and I.L. MacDonald. 2009. Hidden Markov Models for Time Series: An Introduction using R. Chapman and Hall, Boca Raton, FL. See page 82.

Author(s)

Jeff Laake