Syllabus
Course description
The course will provide the opportunity to tackle real world problems requiring advanced computational skills and visualisation techniques to complement statistical thinking. Students will practice proposing efficient solutions, and effectively communicating the results with stakeholders.
Content
Modern statistical computing environments (e.g., R, Julia, and Python)
Aids to efficiency and reproducibility (e.g., GitHub, Markdown)
Data management, wrangling, and ethics
Statistical graphics (grammar, good practices, applications, and examples)
Kernel density estimation and smoothing
Cross-validation
EM algorithm and applications
Resampling methods for uncertainty assessment (bootstrap, jackknife, cross-validation), with applications to regression, time series and dependent data
Monte Carlo methods for sampling and numerical integration
Introduction to Bayesian inference
Markov chain Monte Carlo techniques (Gibbs sampler, Metropolis-Hastings algorithm, Hamiltonian Monte Carlo, convergence diagnostics)
Decision trees for classification
Prerequisites
Required courses: Probability and statistics, Linear models
Learning Outcomes
By the end of the course, the student must be able to:
- Plan complex visualisation and computational tasks
- Perform complex visualisation and computational tasks
- Implement reproducible computational solutions to statistical problems in modern environments and platforms
- Expound the main approaches used for problem solving
Transversal skills
- Take feedback (critique) and respond in an appropriate manner
- Demonstrate the capacity for critical thinking
- Identify the different roles that are involved in well-functioning teams and assume different roles, including leadership roles
- Write a scientific or technical report