Capture-recapture population estimation in continuous time / Kenneth Ray Wilson.
Material type:
TextPublication details: Fort Collins, CO : Colorado State University, 1991.Description: vii, 160 leaves : ill. ; 28 cmOnline resources: Abstract: Continuous time capture-recapture (CR) population estimators were evaluated using Monte Carlo simulations. Three estimators allowed time variation in capture probabilities, p, (Mt - one estimator assumed animals were captured in groups). Two estimators allowed heterogeneous variation in p, also (Mth). CR data were generated using 3 sources of variaton in p: time, behavior, and heterogeneity. Three populations, N,(25, 100, and 500); average capture probabilities, p, (0.1, 0.25, and 0.5); and occasions (6, 10, and 14 days) were simulated. Coeffcient of variation in p (CV(p)), 0.3 and 0.5, was used to simulate heterogeneity.Behavior was simulated for trap happy and trap shy conditions. Group size averaged 2, 3, and 4 for the group estimator. For Mt estimators,when time variation was simulated, percent relative bias (PRB) and percent confidence interval coverage (COV) were generally <10% and >94%,respectively, while CV(N) was generally <10% for p > 0.1, except for the group Mt estimat
| Item type | Current library | Collection | Call number | Status | Date due | Barcode |
|---|---|---|---|---|---|---|
Electronic Report
|
Electronic Library | Non-fiction | WIL (Browse shelf(Opens below)) | Available | 1611 |
Thesis(Ph.D.)--Colorado State University, 1991.
Includes bibliographical references (leaves 158-160).
Continuous time capture-recapture (CR) population estimators were evaluated using Monte Carlo simulations. Three estimators allowed time variation in capture probabilities, p, (Mt - one estimator assumed animals were captured in groups). Two estimators allowed heterogeneous variation in p, also (Mth). CR data were generated using 3 sources of variaton in p: time, behavior, and heterogeneity. Three populations, N,(25, 100, and 500); average capture probabilities, p, (0.1, 0.25, and 0.5); and occasions (6, 10, and 14 days) were simulated. Coeffcient of variation in p (CV(p)), 0.3 and 0.5, was used to simulate heterogeneity.Behavior was simulated for trap happy and trap shy conditions. Group size averaged 2, 3, and 4 for the group estimator. For Mt estimators,when time variation was simulated, percent relative bias (PRB) and percent confidence interval coverage (COV) were generally <10% and >94%,respectively, while CV(N) was generally <10% for p > 0.1, except for the group Mt estimat