Course Overview
This course will address basic methods and modern developments in computational statistics including the frequentist and Bayesian perspective, linear and nonlinear regression, maximum likelihood method, jackknife and bootstrap, principal component analysis, Markov chain Monte Carlo methods, and a brief introduction to information theory, pattern recognition, and machine learning. It is aimed at upper division undergraduates and first year graduate students. Basic familiarity with calculus and linear algebra are the only prerequisites. Some familiarity with probability concepts is helpful though not needed as the lectures include a self-contained introduction to basic probability theory. Matlab tools will provide the computational framework.
Plan for the course material
- Basik probability concepts
- Frequentist and Bayesian views
- Linear and nonlinear regression
- Maximum likelihood
- Bootstrap
- Jackknife
- Markov chain Monte Carlo
- Machine learning