Level: Bachelor’s
Institution: University of Tübingen
Department: Geosciences
My contribution: Lectures + practical sessions (R-based statistics)

Overview

This course provides a structured introduction to the fundamentals of statistics for geoscientists. It combines a conceptual (theory) component with a practical lab component, where students learn how to implement statistical methods in R and interpret results in a scientific and reproducible way. The emphasis is on selecting appropriate methods, understanding assumptions, and communicating results clearly.

Learning objectives

By the end of the course, students will be able to:

• summarize and visualize data using appropriate descriptive statistics
• understand probability concepts relevant to inference (sampling, distributions, uncertainty)
• formulate hypotheses and apply statistical hypothesis testing
• choose and apply common statistical tests and interpret p-values and confidence intervals responsibly
• perform and interpret ANOVA and post-hoc comparisons
• fit and evaluate regression models (with diagnostics and interpretation)
• implement complete statistical workflows in R, including data preparation, analysis, and reporting

Teaching format

The course is structured in two complementary parts:

1) Theoretical sessions

Topics include:

• descriptive statistics, data types, and exploratory data analysis
• probability concepts and sampling distributions
• statistical inference: confidence intervals and hypothesis testing
• parametric vs. non-parametric methods (conceptual overview)
• ANOVA and experimental design basics
• correlation, regression, model interpretation
• assumptions, diagnostics, and common pitfalls in applied statistics

2) Practical sessions (R-based)

Students work with example datasets (often from geoscience contexts) to:

• import, clean, and structure datasets for analysis
• create informative plots and summaries (EDA)
• implement hypothesis tests and interpret outputs
• run ANOVA models and evaluate group differences
• build regression models and check assumptions (residuals, outliers, leverage)
• report results with reproducible scripts and clear figures/tables

Key topics

• Exploratory data analysis (EDA) and visualization
• Hypothesis testing (t-tests and related methods)
• ANOVA and multiple comparisons
• Correlation and linear regression
• Model diagnostics and interpretation
• Reproducible statistical workflows in R

Tools

• R (data handling, statistics, visualization)
• RStudio (development environment)
• Common packages (depending on course setup): ggplot2, dplyr, stats, car, lme4 (intro if needed)

If you are a student in this course and need access to scripts, datasets, or assignment instructions, please contact me.