Edge effects in line intersect sampling with segmented transects

• Published in: Journal of agricultural, biological, and environmental statistics Vol. 10; no. 4; pp. 460 - 477
• Main Authors: Affleck, D.L.R, Gregoire, T.G, Valentine, H.T
• Format: Journal Article
• Language: English
• Published: Washington, DC American Statistical Association and the International Biometric Society 01-12-2005; American Statistical Association; International Biometric Society; Springer Nature B.V
• Subjects: Agronomy. Soil science and plant productions; Asymmetry; Bias; Biological and medical sciences; Biometrics, statistics, experimental designs, modeling, agricultural computer applications; boundary overlap; Configuration management; dead wood; Edge effect; Edge effects; edge effects bias; Environmental sciences; Estimators; Forest ecology; Forest management; Forest service; Forestry research; Fundamental and applied biological sciences. Psychology; Generalities. Biometrics, experimentation. Remote sensing; Inference; Polygons; Population ecology; Sampling; Sampling bias; statistical analysis; Straight lines; surveys; transect configuration; vegetation cover; Transect configuration; Reflection method; Edge effect; Boundary overlap; Overlap; Method; Sampling; Inclusion region
• ISSN: 1085-7117; 1537-2693
• DOI: 10.1198/108571105X81355

Transects consisting of multiple, connected segments with a prescribed configuration are commonly used in ecological applications of line intersect sampling. The transect configuration has implications for the probability with which population elements are selected and for how the selection probabilities can be modified by the boundary of the tract being sampled. As such, the transect configuration also effects the performance of methods designed to eliminate edge-effect bias. We show that the reflection method solves the edge-problem for designs that use symmetric radial transects (e.g., straight-line and X-shaped transects centered at the sample point). This method also applies to designs that use asymmetric radial transects, provided the orientation is selected uniformly at random. Asymmetric radial transects include straight lines emanating from the sample point, and L- and Y-shaped transects. The reflection method does not apply to designs where polygonal transects (e.g., triangular, square, and hexagonal transects) are used, or where the orientations of asymmetric radial transects are fixed. We provide a new method that eliminates edge-effect bias for designs that use asymmetric radial transects with fixed orientation, but a workable solution for polygonal transects remains elusive.