Statistical Methods for Data Science
Sapienza University of Rome ยท M.Sc. in Data Science
Overview
This is a two-semester course (Fundamentals of Statistical Learning I & II) providing the core foundations of statistical inference for data science.
It covers both frequentist and Bayesian paradigms, with applications in estimation, hypothesis testing, model checking, and forecasting.
๐ Complete course information โ Part I
๐ Complete course information โ Part II
Main objectives
- Build and analyze probabilistic models for observed phenomena
- Learn estimation, hypothesis testing, model validation, and forecasting
- Compare frequentist vs Bayesian approaches
- Apply simulation-based methods: Bootstrap, Monte Carlo, MCMC
- Develop statistical computation skills in R, JAGS, OpenBUGS, Stan
Learning outcomes
- Understand both theory and practice of inference methods
- Implement inference tasks with probabilistic programming tools
- Gain hands-on experience with Bayesian modeling (Monte Carlo, MCMC)
- Communicate results effectively via reports, presentations, and visualizations
- Build critical judgment to evaluate and contrast alternative strategies
My work in this course
- Notes & Materials
- Projects