## Abstract

A planted population of known size is added to a target population of unknown size. The populations behave independently, and, for each population, sightings of any member occur according to a Poisson process, which may be time-inhomogeneous. Assuming that the Poisson processes are independent, and the intensity function is the same for all individuals, consideration is given to estimators of the size of the target population, based on observation of the augmented population for a fixed time. The results obtained suggest that the use of plants is beneficial, and that the harmonic mean estimator performs more satisfactorily than other estimators. The robustness of this performance is investigated in the case where the intensity function of the plants may differ from that of individuals from the target population.

Original language | English |
---|---|

Pages (from-to) | 433-451 |

Number of pages | 19 |

Journal | Communications in Statistics: Theory and Methods |

Volume | 27 |

Publication status | Published - 1998 |

## Keywords

- harmonic mean estimator
- inhomogeneous Poisson process
- mark-recapture
- maximum likelihood
- non-central Stirling number
- occupancy distributions
- Petersen estimator
- software reliability
- SAMPLE
- NUMBER
- SYSTEM