Description Usage Details Author(s) References
Example data sets for pcurve package.
1 2 3 4 |
sim4var.txt
Simulated data. Comprises 4 response variables (Taxa1 - Taxa4) and the generating locations (Location). Number of cases = 100. This example was worked by De'ath (1999). The response curves are Gaussian and noise is Poisson. Most starting configurations are adequate, square root transformation helps.
sim10var.txt
Simulated data. Comprises 10 response variables (Taxa1 - Taxa10) and the generating locations (Location). Number of cases = 100. The response curves are Gaussian and noise is Poisson. The beta-diversity is high and recovering the generating locations is difficult. A more difficult exercise. Transformation is a must (square-root is ok). Many starting configurations fail. CA or MDS-BC succeed with appropriate smoothness.
fish.txt
Comprises counts on 10 families of reef fish (n = 33) and a factor variable IMO denoting the position of the sites across the reef. Log-transformation is effective and a final cross-validation helps improve the fit. The locations vary systematically with cross shelf position (IMO).
soilspec.txt
Comprises data on 8 species of plants and 3 soil characteristics and their interactions. Source Gittins (1985), where a relatively complex canonical analysis was used to model the data. This example was worked by De'ath (1999).
R port by Chris Walsh cwalsh@unimelb.edu.au from S+ library by Glenn De'ath g.death@aims.gov.au.
De'ath, G. 1999 Principal Curves: a new technique for indirect and direct gradient analysis. Ecology 80, 2237–2253.
Gittins, R. 1985 Canonical Analysis. A review with applications in ecology. Berlin: Springer-Verlag.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.