Five samples were obtained from each of 112 State parks across New Jersey in both the summer and fall seasons. Each sample was examined using particle-size distribution, pH analysis in both water and 1 M CaCl2, and a loss on ignition technique. Data from each of the techniques were combined, and principal component analysis PCA and canonical discriminant analysis CDA were used for multivariate data transformation. Samples from different locations could be visually differentiated from one another using these multivariate plots. Hold-one-out cross-validation analysis showed error rates as low as 3.33 percent. Ten blind study samples were analyzed resulting in no misclassifications using Mahalanobis distance calculations and visual examinations of multivariate plots. Seasonal variation was minimal between corresponding samples, suggesting potential success in forensic applications. Abstract published by arrangement with John Wiley & Sons.
Downloads
Similar Publications
- The Role of Simulated Data in Making the Best Predictions (from the 87th Annual Meeting of the American Association of Physical Anthropologists - 2018)
- Design and Testing of a Computational Aid for Fire Debris Data Interpretation
- Genetic Architecture of Skin and Eye Color in an African-European Admixed Population