Abstract

We construct 90% normal, percentile, and bias-corrected and accelerated confidence intervals using a finite population bootstrapping algorithm based on adaptive sampling in an agroecosystem. We evaluate the interval estimates based on sampling simulations of a spatially arranged population of plots that contain counts of beet webworms and based on an adaptive condition that generates small networks. The sampling distributions of the original sample estimates and of the bootstrap estimates were generally similar and symmetric. The simulation coverages were from 84% to 90% and similar under any of the sample sizes and any of the three confidence interval types. This study also serves as an example of how adaptive sampling may be used to estimate population characteristics of insects in agroecosystems.

Keywords

Beet webworms, coverage, Horvitz-Thompson estimation, Sitter bootstrapping

Creative Commons License


This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Share

COinS
 
Apr 27th, 1:30 PM

BOOTSTRAP CONFIDENCE INTERVALS FROM ADAPTIVE SAMPLING OF AN INSECT POPULATION

We construct 90% normal, percentile, and bias-corrected and accelerated confidence intervals using a finite population bootstrapping algorithm based on adaptive sampling in an agroecosystem. We evaluate the interval estimates based on sampling simulations of a spatially arranged population of plots that contain counts of beet webworms and based on an adaptive condition that generates small networks. The sampling distributions of the original sample estimates and of the bootstrap estimates were generally similar and symmetric. The simulation coverages were from 84% to 90% and similar under any of the sample sizes and any of the three confidence interval types. This study also serves as an example of how adaptive sampling may be used to estimate population characteristics of insects in agroecosystems.