Simulation-based sampling optimization in multivariate community ecology

This repository contains the data subsets and R code required to reproduce the analyses and figures presented in the manuscript “How much sampling is enough in multivariate community ecology? A simulation-based cost–benefit framework”. The materials support the simulation-based estimation of a priori pseudo-power and the evaluation of cost-efficient sampling designs for multivariate community data, as implemented in the ecocbo framework. The repository includes the following files: dataMacro.csvSubset of the beach macrofauna dataset used to illustrate a one-way design with small effect sizes, based on organism counts across tidal zones. dataEpi.csvSubset of the mangrove-root epibenthic assemblage dataset used to demonstrate a nested hierarchical design with large effect sizes, based on percent cover data. dataFish.csvSubset of the reef fish biomass dataset from Puerto Rico, used to evaluate sampling effort under subtle regional differences and hierarchical designs. figures.RR script containing all code required to reproduce the analyses and generate Figures 2–3 of the manuscript, including data preprocessing, simulations, power estimation, cost–benefit optimization, and graphical outputs. All datasets provided here are reduced and derived versions of the original sources cited in the manuscript, included solely for reproducibility of the results and figures. The complete datasets remain available from their original repositories and publications.