Related Experiment Video
Updated: May 21, 2026

Assisted Selection of Biomarkers by Linear Discriminant Analysis Effect Size (LEfSe) in Microbiome Data
Published on: May 16, 2022
Short communication: Linear discriminant analysis and type of oil added to dairy goat diets
A L Martínez Marín1, P Gómez-Cortés, A G Gómez Castro
1Departamento de Producción Animal (Universidad de Córdoba), Ctra. Madrid-Cádiz, km 396, Campus de Rabanales, 14014 Córdoba, Spain.
Abstract:
Gas chromatography fatty acid (FA) analysis of 112 milk fat samples from dairy goats fed a basal diet with no added oil or the same diet with 1 of 3 vegetable oils added [high oleic sunflower oil (HOSFO), regular sunflower oil (RSFO), or linseed oil (LO)] was used to identify the type of diet consumed through linear discriminant analysis. Twenty variables (19 FA and 1 FA ratio) were selected as valid predictors out of 84 variables tested. The Mahalanobis squared distance was minimal between HOSFO and RSFO groups and maximal between control and LO groups. Cross-validation showed that only one observation from RSFO group was misclassified into the HOSFO group. We concluded that linear discriminant analysis is a useful method to classify milk fat samples from dairy goats according to the particular vegetable oil (of the 3 oils tested here) added to the basal diet.

