Robustness of survival estimates for radio-marked animals
Biometric Bulletin
By: C. M. Bunck and C.-L. Chen
Links
- The Publications Warehouse does not have links to digital versions of this publication at this time
- Download citation as: RIS | Dublin Core
Abstract
Telemetry techniques are often used to study the survival of birds and mammals; particularly whcn mark-recapture approaches are unsuitable. Both parametric and nonparametric methods to estimate survival have becn developed or modified from other applications. An implicit assumption in these approaches is that the probability of re-locating an animal with a functioning transmitter is one. A Monte Carlo study was conducted to determine the bias and variance of the Kaplan-Meier estimator and an estimator based also on the assumption of constant hazard and to eva!uate the performance of the two-sample tests associated with each. Modifications of each estimator which allow a re-Iocation probability of less than one are described and evaluated. Generallv the unmodified estimators were biased but had lower variance. At low sample sizes all estimators performed poorly. Under the null hypothesis, the distribution of all test statistics reasonably approximated the null distribution when survival was low but not when it was high. The power of the two-sample tests were similar.
| Publication type | Article |
|---|---|
| Publication Subtype | Journal Article |
| Title | Robustness of survival estimates for radio-marked animals |
| Series title | Biometric Bulletin |
| Volume | 9 |
| Issue | 3 |
| Year Published | 1992 |
| Language | English |
| Contributing office(s) | Patuxent Wildlife Research Center |
| Description | 8 (Abstract) |
| Larger Work Type | Article |
| Larger Work Subtype | Journal Article |
| Larger Work Title | Biometric Bulletin |
| First page | 8 (Abstrac |
| Google Analytic Metrics | Metrics page |