This class introduces key ideas in probability and statistics as they relate to modern data science, with an emphasis on distributional thinking. The course consists of three components: probability, decision-making under uncertainty, and statistical inference. Topics include: basic probability; expected utility maximization; Law of Large Numbers; maximum likelihood estimation; hypothesis tests, p-values and confidence intervals; kernel density estimation; bias-variance trade-off; linear regression; logistic regression; k-nearest neighbors; classification and regression trees.
Spring 2024
Tuesdays and Thursdays 12:00-1:15 pm
ED 320
Professor Richard Hahn
prhahn@asu.edu
WXLR 529
Zoom Office: https://asu.zoom.us/my/p.richard.hahn
Office Hours by appointment. Monday 10:30am - 11:45am I will keep free. Wexler Hall room 529.
Teaching Assistant
Palak Jain
Help Room Hours Mondays and Thursdays 10:00 - 11:30 in Wexler Hall room 303.
January 9 & 11
Introductions. What is a Statistical Pattern? Probability Basics; Law of Total Probability; Conditional Probability; The Monty Hall problem.
January 16 & 18
Random variables; multivariate random variables; functions of random variables.
January 23 & 25
Binomial distribution; normal distribution; Central Limit Theorem.
January 30 & February 1
Other common parametric distributions; maximum likelihood estimation; finite mixture models.
February 6 & 8
Expected utility maximization. The Kelley Criterion (extended example).
February 13 & 15
Estimand, estimator, estimate; empirical distributions; Law of Large Numbers.
February 20 & 22
Empirical risk minimization; maximum likelihood estimation (MLE).
February 27 & 29
Kernel density estimation; regularization and data-splitting.
March 12 & 14
Linear regression.
March 19 & 17
Classification; ROC curves; logistic regression.
March 26 & 28
k-nearest neighbor classification; regression and classification trees.
April 2 & 4
Individual conditional expectation (ICE) plots.
April 9 & 11
Problem set review.
April 16 & 18
Omitted variable bias; randomized controlled experiments; A/B testing.
April 23 & 25
TBA