Abstract
Contemporary biological assemblage composition and biodiversity are often shaped by a range of natural environmental factors, human disturbances, and their interactions. It is critical to disentangle the effects of individual natural variables and human stressors in data analysis to support management decision-making. Many statistical approaches have been proposed and used to estimate the biological effects of individual predictors, which often correlated and interacted with one another. In this article, we review nine of those approaches in terms of their strengths, limitations, and related r packages. Among those are hierarchical partitioning, propensity score, the sum of AIC weights, structural equation modeling, and tree-based machine learning algorithms. As no approach is perfect, we offer two suggestions: (1) reducing the number of predictors as low as possible by carefully screening all candidate predictors based on biological and statistical considerations; (2) selecting two or more approaches based on the characteristics of the given dataset and specific research goals of a study, and using them in parallel or sequence. Our review could help ecologists to navigate through this challenging process.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
