Class Schedule

Class: Tuesday / Thursday, 1:45-3pm

Office Hours:

Date

Topic

Do Before Class

In-Class Exercise

Th, Jan 6

Course Overview

Tu, Jan 11

CI: Potential Outcomes Framework

Th, Jan 13

CI: Potential Outcomes Framework

  • Exercise

  • Thinking about AB Testing Discussion

Tu, Jan 18

CI: AB Testing / Experiments

  • Angrist and Piscke (MHE) Part 1 (pages 3-24)

  • Kennedy (GtE), pp. 18-21, Notes for 2.8

  • Kennedy (GtE), pp. 241-244, Notes Optional

  • Review linear regression in Python (WM Chapter 13, 13.1, 13.2, 13.3)

Optional:

  • Wooldridge, Section 15.2

Th, Jan 20

CI: AB Testing / Experiments

  • Limitations of Experiments and ATE

  • Internal v. External Validity

  • Stopping Early

Tu, Jan 25

CI: AB Testing / Experiments

  • Evaluating studies

  • Testing in industry

  • SUTVA

  • Evaluating Studies

  • Imbens and Rubin (CI), Section 1.6 (SUTVA, p. 10-13)

  • Kohavi, Tang and Xu, Chpt 1, 2, 3, 4, 22

(Note that Imben & Rubin potential outcomes notation is a little different – just skip notational parts if needed)

Th, Jan 27

CI: AB Testing / Experiments

  • Kohavi, Tang and Xu, Chpts 1, 2, 3, 5, 19, 22

Tu, Feb 1

CI: AB Testing / Experiments

  • Kohavi, Tang and Xu, Chpts 1, 2, 3, 5, 19, 22

Th, Feb 3

CI: AB Testing / Experiments

  • Compliance

Experiments recap

Tu, Feb 8

CI: AB testing Review

Th, Feb 10

CI: Regression

Optional but encouraged:

Tu, Feb 15

CI: Fixed Effects and Clustering

Optional:

  • Kennedy (GtE), Chpt 18.

Th, Feb 17

CI: Matching

Watch the video above from about 15 minutes in (where link starts) till at least 45 minutes in, keep going if you want to learn about propensity score matching problems.

Tu, Feb 22

CI: Difference-in-Differences

Optional but encouraged: (dont need to follow everything, but here’s a real diff-in-diff)

Th, Feb 24

  • CI: Regression Discontinuity

  • Teams

Tu, Mar 1

Backwards Design

Th, Mar 3

Answering Questions

Tu, Mar 8

NO CLASS

Spring Break

Th, Mar 10

NO CLASS

Spring Break

Tu, Mar 15

Taxonomy of Questions

Types of Questions

Th, Mar 17

MIDTERM

MIDTERM

Tu, Mar 22

Workflow Management

Th, Mar 24

Descriptive Questions

Link

Tu, Mar 29

Prediction: ML Bias

Examples of AI Bias:

Optional:

Th, Mar 31

Prediction: Are interpretable models enough?

Optional:

(Don’t expect to follow everything in that… just a heads up it exists!)

Tu, Apr 5

Prediction: ML versus Casual Inference

Th, Apr 7

Practice Presentations

  • Modelling of Presentations and Feedback

  • PROJECT ROUGH DRAFTS DUE

Tu, Apr 12

Course Summary Class

**LAST CLASS*

Texts Referenced in Schedule: