|
Abstract:
|
Measurement error and missing data are two common problems in wildlife population surveys. These data are collected from the environment and may be missing or measured with error when the observer’s ability to see the animal is obscured. Methods such as video transects for estimating Red Snapper abundance are highly affected by these problems since abundance will be underestimated if missing/mismeasured counts are ignored. We shall refer to this problem as visibility bias. It occurs when the true counts of animals are observed, partially observed (mismeasured), and unobservable (missing) when visibility is high, degraded, and lost respectively. Furthermore, data from animal population surveys are often zero-inflated since not all sampled regions are inhabited by the species. In this paper, we examined several multiple imputation methods to handle count data that are subject to visibility bias and have excess zeros including: Bayesian hierarchical models, modified hotdeck, predictive mean matching, normal, Poisson, and zero inflated Poisson imputation. We performed a simulation study to examine their performance for estimating total abundance and habitat occupancy rate.
|
