# Multivariate HMM object

### Description

The multivariate HMM object is output of the function `callPeaksMultivariate`

and is a `list()`

with various entries. The class() attribute of this list was set to "multiHMM". For a given hmm, the entries can be accessed with the list operators 'hmm[[]]' or 'hmm$'.

### Value

A `list()`

with the following entries:

`IDs` |
IDs of the input univariate HMMs. |

`bins` |
A |

`segments` |
Same as |

`mapping` |
A named vector giving the mapping from decimal combinatorial states to human readable combinations. |

`weights` |
Weight for each component. Same as |

`weights.univariate` |
Weights of the univariate HMMs. |

`transitionProbs` |
Matrix of transition probabilities from each state (row) into each state (column). |

`transitionProbs.initial` |
Initial |

`startProbs` |
Probabilities for the first bin. Same as |

`startProbs.initial` |
Initial |

`distributions` |
Emission distributions used for this model. |

`post.cutoff` |
False discovery rate. NULL means that the state with maximum posterior probability was chosen, irrespective of its absolute probability (default=NULL). |

`convergenceInfo` |
Contains information about the convergence of the Baum-Welch algorithm. |

`convergenceInfo$eps` |
Convergence threshold for the Baum-Welch. |

`convergenceInfo$loglik` |
Final loglikelihood after the last iteration. |

`convergenceInfo$loglik.delta` |
Change in loglikelihood after the last iteration (should be smaller than |

`convergenceInfo$num.iterations` |
Number of iterations that the Baum-Welch needed to converge to the desired |

`convergenceInfo$time.sec` |
Time in seconds that the Baum-Welch needed to converge to the desired |

`correlation.matrix` |
Correlation matrix of transformed reads. |

### See Also

`callPeaksMultivariate`

, `uniHMM`

, `combinedMultiHMM`

### Examples

1 2 3 4 | ```
## Get an example multiHMM
file <- system.file("data","multivariate_mode-combinatorial_condition-SHR.RData",
package="chromstaR")
model <- get(load(file))
``` |