Applied Statistics, from Data to Interpretation

The course is designed to provide doctoral students with the fundamental statistical tools needed to analyze and interpret biological data, with a focus on omics studies in the field of food systems. The course begins with an introduction to the fundamentals of descriptive statistics, covering essential concepts such as measures of central tendency, variability, and probability distributions. Students will gain proficiency in data visualization through histograms, boxplots, and bar charts, which will provide a solid foundation for understanding the underlying patterns in their data sets. Moving on to inferential statistics, the course explores hypothesis testing, including techniques such as the Student t-test, nonparametric tests, and ANOVA, all of which are essential for comparing groups and drawing conclusions from sample data. The course then explores multivariate analysis, with a focus on methods such as Principal Component Analysis (PCA) and cluster analysis, essential for understanding complex, high-dimensional data. Specific techniques such as LEfSe, DESeq2, CLR, and PERMANOVA will be introduced to help students manage omics data and identify meaningful patterns. A significant component of the course includes hands-on experience with R, a powerful statistical analysis software. Students will learn to use R to perform descriptive and inferential statistics and visualize data using R libraries. The course also introduces students to the concepts of regression, correlation, and machine learning (e.g., decision trees and random forest models), all of which are increasingly important in data-driven research.