How to test the missing data mechanism in a hidden Markov model

A Hidden Markov Model with missing data in the outcome variable is considered. The initial and transition probabilities of chain emission probability HMM are allowed to depend on fully observed covariables. Tests for ignorable MCAR mechanisms proposed. These tests do not require grouping individuals by their pattern, making them easier apply practice. They based estimates conditional emitting a given latent state some When mechanism holds, value same variables. On contrary, when these all same. practical implementation simulations proposed, along presentation performances. real example from piglet farming illustrates use.