METHODOLOGY: DISCRIMINANT FUNCTION ANALYSIS OF COMPOSITIONAL DATA: AN EXAMPLE FROM HYDRAULIC GEOMETRY Academic Article uri icon

abstract

  • Many of the data sets analyzed by physical geographers are compositional in nature: they have row vectors that add to one (or 100%). These unit-sum constrained data sets should not be analyzed by standard multivariate statistical methods. Significant differences were found in the log-ratio mean vectors of the hydraulic exponents (which are unit-sum constrained) for two classes of streams: those with cohesive, non-vertical banks, and those with one firm and one loose bank. Compositional discriminant function analysis of bank stability on the basis of hydraulic geometry had a success rate of 88%, making routinely archived measurements of stream width, cross-sectional area, mean velocity, and discharge a readily available data base for predicting the stability of stream reaches. 1994 Taylor & Francis Group, LLC.

published proceedings

  • Physical Geography

author list (cited authors)

  • Ridenour, G. S., & Giardino, J. R.

citation count

  • 7

publication date

  • January 1994