Biostatistics

Assays in experimental biology generate large amounts of data that must be critially assessed and
processed appropriately to extract meaningful biological knowledge and generate testable
hypotheses. Proficiency in data wrangling and data visualisation, the ability to unravel complex
relationships in biological data and the ability to create transparent and reproducible workflows
constitute crucial skills for the modern biologist. In addition, a good understanding of principles of
experimental design are central to the critical assessment of experimental data. With data as the focus
and R/RStudio as the tool, students are exposed and trained in a unified view of experimental design
and data analysis. Students will develop expertise in data organisation, visualisation, analysis and
interpretation using both conventional biological data and complex large scale (BIG) biological data.
The aims of this course are to enable students to (i) analyse data from a well-designed biological
experiment, (ii) create a transparent reproducible analysis workflow using Rmarkdown in R/Rstudio
that includes exploratory analyses, statistical modelling, model assessment and parameter estimation,
(iv) understand the power and pitfalls of statistical analyses, (v) implement methods for the analysis
of gene expression (RNA-Seq) data and the interpretation of the final results.
Throughout the course, we will use R programming language and the R/Studio software environment.

1. Use the R/RStudio environment to import, visualise, wrangle and summarise data.
2. Create transparent reproducible analysis workflows using Rmarkdown.
3. Understand the statistical model framework for statistical inference and estimation.
4. Interpret results from statistical models using ANOVA tables and estimated marginal means.
5. Communicate conclusions of statistical analyses in graphs and/or tables.
6. Correctly analyse, interpret and visualize the results of dirrerential gene expression
analyses, based on RNA sequencing data