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
- Beyond the Courtroom - A Comparative Analysis of Misdemeanor Sentencing
- Patterns of Concordance Between Hair Assays and Urinalysis for Cocaine: Longitudinal Analysis of Probationers in Pinellas County, Florida (From The Validity of Self-Reported Drug Use: Improving the Accuracy of Survey Estimates, P 161-199, 1997, Lana Harri
- Developing and Using a Serious Drug Abuser Scale in the Criminal Justice System: Executive Summary