rEMM (version 0.1-2)

transition_table: Extract a Transition Table for a New Sequence Given an EMM

Description

Finds the state sequence of a new sequence in an EMM and returns a table with the transition probabilities or counts.

Usage

## S3 method for class 'EMM,matrix':
transition_table(x, newdata, method = c("prob", "counts", "log_odds"), match_state = "nn", plus_one=TRUE, initial_transition = FALSE)

Arguments

x

an EMM object.

newdata

new sequence,

method

the measure to return.

match_state

do the new observations have to fall within the threshold of state ("exact") or is nearest neighbor used ("nn")?

plus_one

add one to each transition count. This is equal to start with one for each transition count, i.e. initially all transitions are equally likely. It prevents the product of probabilities to be zero if a transition was never observe

initial_transition

include the initial transition in the table?

Value

• A data.frame with three columns (from state, to state and the transition probability/count.)

See Also

transition to access transition probabilities and find_states for assigning observations to states/clusters.

Examples

data("EMMsim")

emm <- EMM(threshold=.5)
emm <- build(emm, EMMsim_train)

transition_table(emm, EMMsim_test)
transition_table(emm, EMMsim_test, method ="prob", initial_transition=TRUE)