Opened 13 years ago

Closed 12 years ago

## #351 closed request (wontfix)

# Estimating parameter p (and confidence interval) in binomial distribution

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

Priority: | minor | Milestone: | |

Component: | statistics | Version: | trunk |

Keywords: | Cc: |

### Description

related to ticket:258

When performing a permutation test you are sampling from a binary (Bernoulli) distribution and number of successes, k, will follow a binomial distribution. Typically the parameter p is obviously estimated as k/n, but I would like some functionality how to calculate confidence interval.

Should check into GSL to see if there is useful support.

I am not sure how the calculation should be performed but I suppose a Baysian approach might be sound, having a uniform distribution on p.

### Change History (2)

### comment:1 Changed 13 years ago by

### comment:2 Changed 12 years ago by

Milestone: | yat 0.x+ |
---|---|

Resolution: | → wontfix |

Status: | new → closed |

This is provided by boost 1.35:

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

This page might bu useful

http://en.wikipedia.org/wiki/Binomial_proportion_confidence_interval