'LMlatent'An S3 class object created by lmest for Latent Markov (LM) model with covariates in the latent model.
maximum log-likelihood
estimated array of the parameters affecting the logit for the initial probabilities
estimated array of the parameters affecting the logit for the transition probabilities
estimate of initial probability matrix. The first state is used as reference category when param = "multilogit"
estimate of transition probability matrices. State u is used as reference category when paramLatent = "multilogit"
estimate of conditional response probabilities (mb x k x r)
number of free parameters
optimal number of latent states
value of the Akaike Information Criterion for model selection
value of the Bayesian Information Criterion for model selection
log-likelihood trace at every step of the EM algorithm
number of observations in the data
number of time occasions
type of parametrization for the transition probabilities ("multilogit" = standard multinomial logit for every row of the transition matrix, "difflogit" = multinomial logit based on the difference between two sets of parameters)
standard errors for the conditional response matrix
standard errors for Be
standard errors for Ga
vector containing the values of the log-likelihood of the LM model with each k (latent states)
vector containing the values of the BIC for each k
vector containing the values of the AIC for each k
array containing the posterior distribution of the latent states for each response configuration and time occasion
matrix containing the predicted sequence of latent states by the local decoding method
array containing the available response configurations
vector of frequencies of the available configurations
matrix containing the marginal distribution of the latent states
command used to call the function
Data frame given in input
Francesco Bartolucci, Silvia Pandolfi, Fulvia Pennoni, Alessio Farcomeni, Alessio Serafini
lmest