Comparing the Linear and Quadratic Discriminant Analysis of Diabetes Disease Classification Based on Data Multicollinearity

Linear and quadratic discriminant analysis are two fundamental classification methods used in statistical learning. Moments (MM), maximum likelihood (ML), minimum volume ellipsoids (MVE), t-distribution to estimate the parameter of independent variables on multivariate normal distribution order classify binary dependent variables. The MM ML popular effective that approximate use observed data. However, MVE focus resampling algorithm, a reliable tool for high resistance. This paper starts by explaining concepts linear then presents four other create decision boundary. Our simulation study generated setting coefficient correlation via or multicollinearity, often through basic logistic regression construct variable. For application Pima Indian diabetic dataset, we expressed diabetes as variable dataset eight aimed determine highest average percentage accuracy. results showed successfully large (LDA). method (QDA) performed better when using small