bevimed_polytomous {BeviMed} | R Documentation |

## Model selection for multiple association models

### Description

Apply bevimed to the no association model (gamma = 0) and multiple association models for different sets of variants, for instance, corresponding to different functional consequences.

### Usage

```
bevimed_polytomous(
y,
G,
ploidy = rep(2L, length(y)),
variant_sets,
prior_prob_association = rep(0.01/length(variant_sets), length(variant_sets)),
tau0_shape = c(1, 1),
moi = rep("dominant", length(variant_sets)),
model_specific_args = vector(mode = "list", length = length(variant_sets)),
...
)
```

### Arguments

`y` |
Logical vector of case ( |

`G` |
Integer matrix of variant counts per individual, one row per individual and one column per variant. |

`ploidy` |
Integer vector giving ploidy of samples. |

`variant_sets` |
List of integer vectors corresponding to sets of indices of |

`prior_prob_association` |
The prior probability of association. |

`tau0_shape` |
Beta shape hyper-priors for prior on rate of case labels. |

`moi` |
Character vector giving mode of inheritance for each model. |

`model_specific_args` |
List of named lists of parameters to use in |

`...` |
Other arguments to pass to |

### References

Greene et al., A Fast Association Test for Identifying Pathogenic Variants Involved in Rare Diseases, The American Journal of Human Genetics (2017), http://dx.doi.org/10.1016/j.ajhg.2017.05.015.

### See Also

*BeviMed*version 5.10 Index]