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.
Comparative Forensic Soil Analysis of New Jersey State Parks Using a Combination of Simple Techniques with Multivariate Statistics
NCJ Number
246841
Journal
Journal of Forensic Sciences Volume: 59 Issue: 3 Dated: May 2014 Pages: 627-636
Date Published
May 2014
Length
10 pages
Annotation
This study has shown that the combination of simple techniques with the use of multivariate statistics offers the potential for the comparative analysis of soil samples.
Abstract
Date Published: May 1, 2014