Skip to content

Week 6: Spatial Sampling and Sampling Bias

Core Questions

  • How does spatial sampling bias influence estimates of biodiversity?
  • How do random, stratified, systematic, clustered, and thinned samples differ?
  • Why are rare species and spatial pseudoreplication especially difficult?

Concepts

  • Random, stratified, and systematic sampling.
  • Spatial clustering.
  • Sampling effort and accessibility bias.
  • Spatial thinning.
  • Rare species.
  • Pseudoreplication.
  • Background and pseudoabsence sampling.

Python Tools

  • GeoPandas.
  • NumPy.
  • scikit-learn.
  • scipy.

Applied Lab

Students compare raw observations, spatially thinned observations, and stratified samples from a biased occurrence dataset, then evaluate how each sampling strategy changes species richness and model-ready data.

Deliverable

Submit a sampling-bias analysis with maps, summary statistics, and a short recommendation for the final project sampling strategy.