In this study, discriminant analysis techniques were
employed to investigate the relationship between sandy soil categories and
macronutrients. Sandy soil has excellent drainage properties due to its coarse
texture. It allows water to infiltrate quickly, preventing water logging and
reducing the risk of root rot. The assumptions of linear discriminant function
analysis, such as the normality of regressors, multicollinearity, and
homoscedasticity were carefully examined. A parametric technique called discriminant
analysis (DA) is used to identify the weightings of quantitative variables or
predictors that best distinguish between two or more categories of dependent
variables. The data were transformed using the Box-Cox method to improve
normality, and a multivariate analysis of variance was employed to determine
whether there were significant differences in soil macronutrients between the
sand groups. The results showed that there were significant differences in soil
macronutrients between the sand groups, and the classification accuracy of the
discriminant function was 67%. The findings suggested that the discriminant
function analysis could be used for classifying soil types based on their
macronutrient content, particularly in sandy soil. By examining the discriminant
weights assigned to each nutrient, and determining pH, EC and OM nutrients have
the most significant impact on the sand categories. This information can be
used to prioritize variables for further investigation.
Author(s) Details:
Rajarathinam A.,
Department of Statistics, Manonmaniam Sundaranar University,
Tirunelveli - 627 012, India.
Ramji M.,
Department
of Statistics, Manonmaniam Sundaranar University, Tirunelveli - 627 012, India.
Please see the link here: https://stm.bookpi.org/RACAS-V3/article/view/13261
