Application of multilinear regression analysis in modeling of soil properties for geotechnical civil engineering works in Calabar South
The application of Multi-Linear Regression Analysis (MLRA) model for predicting soil properties in Calabar South offers a technical guide and solution in foundation designs problems in the area. Forty-five soil samples were collected from fifteen different boreholes at a different depth and 270 tests were carried out for CBR, MC, SG, LL, PL test and GS with mechanical sieve analysis of sizes, 2.36 mm, 1.18 mm, 600 μ, 425 μ, 300μ, 212μ, 150μ, and 75μ. This study uses Multi Linear Regression Analysis to formulate a model that relates CBR to other soil parameters. The Multi Linear Regression Analysis was done using the Data Analysis tool of Microsoft Excel, which gave a good coefficient of correlation R2, 0.9454 implying that the model can be used to predict CBR at 50.9 % and with ±3.4% error. This conclusion is drawn since the value of R2 increases with increase in numbers of variables.
Keywords: Calabar, CBR, Model, Regression, Soil properties, Soil Samples