covariate_ci: Compute transition probability matrices for plotting
In simonecollier/lizardHMM: Fitting Lizard Movement Data with HMMs

This function computes the transition probability matrix entries with their confidence intervals for different covariate values in order to plot how they change. THIS FUNCTION DOES NOT SUPPORT UNPOOLED TRANSITION PROBABILITY MATRICES.

covariate_ci(
  hmm,
  len_covariates,
  design,
  n = 100,
  level = 0.975,
  state_dep_dist_pooled = FALSE
)

`len_covariates`	A value indicating how many covariate values will be used.
`design`	A list of design matrices, one for each subject which indicate the values of the each of the covariates (column) at each point in time (row).
`num_states`	The number of states in the desired HMM.
`num_subjects`	The number of subjects/trials that generated the data.
`num_covariates`	The number of covariates in the data that the transition probability matrix depends on.
`conf_intervals`	A list of the confidence intervals for each fitted parameter of the HMM as outputted by the functions `norm_ci`, `gam_ci`, or `gam0_ci`.

A list of 3 matrices, one for the estimate and the upper, and lower confidence interval, with the rows of the matrices containing the entries of the transition probability matrices at each covariate value.

simonecollier/lizardHMM documentation built on Dec. 23, 2021, 2:24 a.m.