The authors discuss their research methodology and findings regarding the combination of using simple techniques and multivariate statistics to analyze soil samples for use in forensic investigations.
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. Five samples were obtained from each of twelve 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. (Published Abstract Provided)
Downloads
Similar Publications
- Naturally-occurring DNA fragment termini correlate with methylation at CpG sites in hair and blood plasma cell-free DNA
- Latent Print Procedures Manual, Virginia Department of Forensic Science
- Evaluation of Digital Evidence Processing Efficiencies in Publicly Funded Crime Laboratories: A Formative Study on how Crime Laboratories and Law Enforcement Ag