Multivariate Models for Studying the Association between Soil Major and Minor Nutrients | Chapter 4 | Research and Applications Towards Mathematics and Computer Science Vol. 6

 An practical investigation was completed activity to study the connection between the soil traits, including the Nitrogen (N), Phosphorus (P), Potassium (K), potential of Hydrogen (pH), Electrical generated power (EC), Sulfur (S,), Zinc (Zn), Iron (Fe), Copper (Cu), Manganese (Mn) and Boron (B) using principal component study (PCA), Factor Analysis (FA), and Canonical Correlation study (CCA) for data decline multivariate techniques. The first five main parts explained 24.22%, 18.52%, 16.1%, 9.97%, and 9.27% of sample variances, respectively. All five principal parts (PCs) accounted for 78.07% of the sample difference. The soil traits viz., P and K have very dominated the first PC; the soil traits N and pH have dominated the second PC; K, EC, and Cu have ruled the tertiary PC; Fe, Mn, and pH have dominated in the one of four equal parts PC; whereas the limit Cu beaten the fifth PC. The first determinant showed a forceful negative stowing on S and a strong definite loading on Cu; P, K, and EC have solid positive loadings in the second determinant. Significant beneficial loadings on Mn, Fe, Cu, pH, N, and K are present in the third component. The divide into four equal parts factor had a considerably beneficial pH, Fe, N, P, K, and B loadings. Fe, P, and B have much weight in the having five of something factor. The soil traits namely., N, Zn, pH, K, Fe, and Mn have dominated the first PC; the soil traits B, P, S, Zn, and Fe have dominated the second PC; B and P have ruled the third PC inasmuch as the only figure Cu dominated the one of four equal parts PC. Cu and OC have much weight in the divide into four equal parts determinant. The canonical redundancies for helpless and independent sets are 12% and 17%, individually. The Stewart-Love canonical repetition index is 70.58%, that means that the first uninterrupted combination of the X-set justifies 70.58% of the total difference in the Y-set.

Author(s) Details:

Rajarathinam, A.,
Department of Statistics, Manonmaniam Sundaranar University, Tirunelveli, Tamil Nadu, India.

Please see the link here: https://stm.bookpi.org/RATMCS-V6/article/view/12523