BIOMETRY AND STUDY OF ANIMAL POPULATIONS

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

• Employ various techniques for the analysis of biological data.
• Understand how analytical techniques (including machine learning techniques) can be used for classification, prediction, and hypothesis testing in biological contexts.
• Explore and visualize biometric data using plots.
• Have a broad knowledge of application cases of data analysis techniques to real biological systems from natural populations.
• Use the R software for low-difficulty data analysis tasks (using existing packages to perform the analytical techniques learned in the course).
• Understand how the data analysis and machine learning techniques learned in the course are typically implemented in software with graphical user interface.

• Lectures: theoretical concepts with practical examples.
• Computer labs: practical applications of data analysis techniques using software (particularly R).

• Basic knowledge of animal biology.
• Knowledge of the English language (needed for reading scientific articles and educational materials).

Attendance at lectures and labs is fundamental for various reasons, including the fact that the technical skills learned during the course are fundamental for the practical part of the final exam.

Module 1: Biometric Tools

• Introduction to biometry and types of data (morphological, genetic, and ecological) from animal populations.
• Data analysis and biometry: statistics, machine learning, and artificial intelligence.
• Exploration and visualization of biological data through plots (e.g., box plots, scatterplots, histograms).
• Comparing two groups: randomization-based methods and other approaches.
• General linear models and their applications.
• Principal Component Analysis (PCA).
• Classification – Discriminant analysis and classification based on biometric data.
• Quantifying the performance of classification models with cross-validation.

Module 2: Applications in Natural Populations

• Case studies involving the application of techniques covered in the first module.
• Applications using morphometric data.
• Ecological data and associated issues.
• Genetics, genomics, and transcriptomics of animal populations.

There are no “adopted” books in the strict sense, and the main reference material will be provided by the instructor. However, some texts are recommended for consultation and further study.

Books for reference and further study

• Sokal, R.R., Rohlf, F.J. Biometry: The Principles and Practice of Statistics in Biological Research, W.H. Freeman.
• Vu, J., Harrington, D. Introductory Statistics for the Life and Biomedical Sciences. Openintro (available at Openintro).

Assessment will be via a theoretical-practical oral exam. An intermediate written test may be scheduled for students attending lectures regularly (details and timing of the written test which will be communicated to the students during the course).

1. Describe how principal component analysis (PCA) can be used to explore a biometric dataset.
2. Explain how cross-validation can be used to test the accuracy of machine learning-based predictive models.