Final grade: 9.5
Practical case grade: 10
This course consisted in working with statistics from a bayesian point of view. We have seen:
- Conjugate distributions
- Gaussian modeling
- Simulation models for bayesian estimation
- Bayesian linear and non-linear regression models
- Bayesian clustering
It mainly consisted on a conceptual part, pen and paper, and a computational part, with R.
During the course, we were assigned to work in a practical case and apply some of the bayesian methodologies we learned in class. In my case, I opted for modeling my daily steps, extracted from my Apple Fitness data. For it I used a Makov Chain Monte Carlo (MCMC) method with an implementation of the Metropolis–Hastings algorithm.