Skip to content
/ MAT331 Public

I designed this statistical modeling course for Stony Brook University. All course materials - python codes, experiments, results, solutions can be found here

Notifications You must be signed in to change notification settings

letaoZ/MAT331

Repository files navigation

Solve Math related questions with Python

Probability, Statistics and Machine Learning
References: 
Grinstead and Snell's Introduction to Probability; 
Advanced Data Analysis from an Elementary Point of View

Detailed class info can be found here

week 01 - introduction to Python, statists VS mathematics

week 02 - Basics in Python. Destributions.

week 03 - numpy and matplotlib in Python. Central Limit Theorem and Law of Large Numbers.

week 04 - Inplement inverse sampling method; Plot "probability". The amazing Normal Distribution - everything is Normal.

week 05- Visualization of Central Limit and Law of Large Number. From central limit to normal, and to Hypothesis testing.

week 06 - ALL linear regressions you can build in Python. Intro to Naive Bayes == maximal likelihood estimation and Linear regression as its applicaiton (without proof, will prove later)

week 07 - seaborn and Mixture model -- graphical representation of "Not so naive Bayes". Review

week 08 -- spring break

week 09 -- Monte Carlo, rejection sampling, importance sampling. More maximal likelihood estimation.

week 10 -- Errors: Monte Carlo, Trapezoid Rule, Left integration. Detailed proof of linear regression as MLE.

week 11 -- Timing code and Matrix operations in Python (numpy is faster). Markov Chain.

week 12 -- properties of different states of Markov chains

week 13 -- Determine Chain types by simulation in Python and by graph operation. Calculate time to absorption and probability.

week 14 -- Ergodic Markov Chain

About

I designed this statistical modeling course for Stony Brook University. All course materials - python codes, experiments, results, solutions can be found here

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages