An Introduction to Probability and Statistics
summary
Covers a hands‑on path from basic counting to Bayesian parameter estimation and generalized linear models, using Python 3 notebooks and concrete code: a “magic coin” that motivates probability rules, SciPy’s binomial and the beta distribution for inference, Monte Carlo sampling with numpy, and a simulated e‑commerce experiment (toothbrush/pencil) that runs A/B tests and a PyMC3/Stan style Bayesian regression. Claims: 90 minutes gets from zero to logistic/GLM; shows a 6/20 (30%) example, how priors and sampling give credible intervals, and how adjusting for a confounder (students) flips the result.
AI-written summary · about
chapters (6)
- 0:00Introduction
- 1:47Coin flip example
- 22:02Probability to statistics
- 28:19Parameter estimation
- 46:00Generalized linear models
- 1:09:54Q&A
related talks
14mProbabilistic Programming in Python
01h 22mDoing frequentist statistics with Scipy
39mProbablistic Programming Data Science with PyMC3
42mBayesian Non-parametric Models for Data Science using PyMC3
01h 22mWriting effective bayesian programs using TensorFlow and TFP
35mMental Models to Use and Avoid as a Data Scientist
29mOn Monte Carlo simulations and the statistics of love
44mAn introduction to PyMC3