Project: Hierarchical Bayesian models to inform parameter estimation and inference

Project

Hierarchical Bayesian models to inform parameter estimation and inference

November 2020 - November 2030

Personnel

Graziella DiRenzo, Principal Investigator

Participating Agencies

Accurate inference for population dynamics relies on intensive data collection methods, where individuals are marked and tracked over time at a small number of sites. Collecting sufficient data at conservation-relevant scales is logistically and financially challenging. These issues led to the development of models for unmarked data, which provide a fully mechanistic framework to estimate demographic rates without the need to track individual capture histories. Such models have been criticized and shown to perform poorly when model assumptions are not met; yet, they continue to be modified to incorporate biological realism (e.g., accommodating stage-structured data). Therefore, in this project, I evaluate the performance and identify tradeoffs in working with different models.

Research Publications

Research Publications	Publication Date
Halstead, B. J., P. M. Kleeman, G. V. DiRenzo, & J. P. Rose. 2022. Occurrence of Shasta salamanders (Hydromantes spp.) in little-studied portions of their range, with implications for optimizing survey design. Journal of Herpetology 56, 218-228. DOI: 10.1670/20-119.	August 2022
DiRenzo, G. V., Hanks, E., & D. A. W. Miller. 2022. A practical guide to understanding and validating complex statistical models using simulations. Methods in Ecology & Evolution 00: 1–15. DOI: 10.1111/2041-210X.14030.	November 2022
DiRenzo, G. V., D. M. W. Miller, & E. H. C. Grant. 2022. Ignoring species availability biases occupancy estimates in single-scale occupancy models. Methods in Ecology & Evolution 13: 1790-1804. https://doi.org/10.1111/2041-210X.13881 \| Abstract \| Publisher Website	May 2022	1. Most applications of single-scale occupancy models do not differentiate between availability and detectability, even though species availability is rarely equal to one. Species availability can be estimated using multi-scale occupancy models, and the availability process includes elements of species movement, behavior, and phenology. However, for the practical application of multi-scale occupancy models, it can be unclear what a robust sampling design looks like and what the statistical properties of the multi-scale and single-scale occupancy models are when availability is less than one.<br><br>2. Using simulations, we explore the following common questions asked by ecologists during the design phase of a field study: (Q1) what is a robust sampling design for the multi-scale occupancy model when there are <i>a priori</i> expectations of parameter estimates?, (Q2) what is a robust sampling design when we have no expectations of parameter estimates?, and (Q3) can a single-scale occupancy model with a random effects term adequately absorb the extra heterogeneity produced when availability is less than one and provide reliable estimates of occupancy probability?.<br><br>3. Our results show that there is a tradeoff between the number of sites and surveys needed to achieve a specified level of acceptable error for occupancy estimates using the multi-scale occupancy model. We also document that when species availability is low (< 0.40 on the probability scale), then single-scale occupancy models underestimate occupancy by as much as 0.40 on the probability scale, produce overly precise estimates, and provide poor parameter coverage. This pattern was observed when a random effects term was and was not included in the single-scale occupancy model, suggesting that adding a random-effects term does not adequately absorb the extra heterogeneity produced by the availability process. In contrast, when species availability was high (> 0.60), single-scale occupancy models performed similarly to the multi-scale occupancy model.<br><br>4. As a companion, we provide an RShiny app that allows users to further explore our results and sampling designs across a number of different scenarios https://gdirenzo.shinyapps.io/multi-scale-occ/. Our results suggest that unaccounted for availability can lead to underestimating species distributions when using single-scale occupancy models, which can have large implications on ecological inference and predictions for practitioners, such as those working at the front lines of invasion ecology, disease emergence, and species conservation.

Cooperative Fish and Wildlife Research Units Program: Education, Research and Technical Assistance for Managing Our Natural Resources

Project

Hierarchical Bayesian models to inform parameter estimation and inference

November 2020 - November 2030

Personnel

Participating Agencies

Cooperative Fish and Wildlife Research Units Program:
Education, Research and Technical Assistance for Managing Our Natural Resources