Opened 6 years ago

Closed 6 years ago

## #847 closed defect (fixed)

# ROC p_value; when is exact method used

Reported by: | Peter | Owned by: | Peter |
---|---|---|---|

Priority: | minor | Milestone: | yat 0.13 |

Component: | documentation | Version: | 0.12.2 |

Keywords: | Cc: |

### Description

Documentation says:

If both number of positive samples, n_pos(void), and number of negative samples, n_neg(void), are smaller than minimum_size the exact method is used.

Implementation says:
*either or*

Which one should it be?

### Change History (2)

### comment:1 Changed 6 years ago by

Component: | statistics → documentation |
---|---|

Milestone: | yat 0.x+ → yat 0.13 |

**Note:**See TracTickets for help on using tickets.

[This paper http://pietrobattiston.it/_media/economics:mww:exact_mww.pdf] concludes that the approximation could be used

if m and n both are large enough, i.e., use exact method if either m or n is small.