Sitemap - 2024 - Scott's Mixtape Substack

S4E10: Ted Joyce, Health Economist, CUNY

Spring 2025 workshops plus camping and personal things

Closing my tabs: the Kerouac edition

Closing my tabs

Personal post

How to tell if ChatGPT wrote the students essays

S4E9: Francine Blau, Gender and Labor Economics, Cornell University

Closing my tabs

Short gap versus Long differences in diff-in-diff event studies: part 2

Closing my tabs

Short gap versus Long differences in diff-in-diff event study: Part 1

A 700 page gorilla of a book has been sent Yale University Press

S4E8: Jann Spiess, Machine Learning and Causal Inference, Stanford

Closing my browser tabs out: Saturday edition

Unconfoundedness, Regression Adjustment, Heterogenous Treatment Effects, LaLonde, Mad Max: Fury Road the Theatrical Version (not the Director's Cut) and MAJOR edits of the 2nd edition of the Mixtape

What I’m thankful for

Back home and under the weather with t-6 days

Closing my Saturday browser tabs

Maybe Ken Chay is the Bridge between Rubin and Princeton, but Only Once He Gets to Berkeley

Implementing my diff-in-diff checklist for the book using county level crime data

S4E7: Elizabeth Cascio, Labor Economist, Dartmouth

Update on the Mixtape Revision

Closing out my open browser tabs

The Final Stretch: Another Mixtape Update

Rant in Defense of the Apple Vision Pro

Today I Am Giving a Talk to Baylor Faculty About Using AI Productively for Research and Here is My Itinerary and Talking Points

Update on the Mixtape Second Edition Revisions

Diff-in-Diff Chapters Done, On To Synthetic Control

Closing my tabs

Can Generative AI Predict Elections? A Qualified Answer

Update on Revision of Mixtape: Countdown t-24

S4E6: Timothy Bartik, Labor Economics, Upjohn Institute

Update on Progress on the Mixtape Revisions

Tips and Thoughts about AI for Research and Teaching College Students

Closing Out My Tabs

Exploring the World of Charles Manski with an AI Generated Podcast Doing a Deep Dive on His Vita

Advanced Transcript: Tim Bartik, Labor Economics, Upjohn Institute

Formalized Argument for Design Being Longer in QCD than RCT: Part 3

Saturday links

An Argument for the QCD (Quasi-Experimental Controlled Design): Part 2

Between Trust and Code

Hidden Curriculum Workshop with Mark Anderson and Dan Rees

S4E5: Miikka Rokkanen, Consumer Behavior Analytics, Amazon

Diff-in-diff papers and their impact

Saturday links

Design Time is a Substitute for Controlled Randomization: Part 1

Causal Panel Workshop and ML and Causal Inference Workshop: a Public Service Announcement

Advanced Transcript: Miikka Rokkanen, Customer Behavior Analytics, Amazon

How I Asked ChatGPT to Help Me Become a Better Grader

Saturday links

My Annual Prediction Ritual of the Nobel Prize in Economics

S4E4: Maya Rossin-Slater, Health Economist, Stanford

Riding the moving sidewalk and the art of prompt coding with LLMs

Saturday Links

Causal Panel workshop

Which artist will history remember as the dominant American singer songwriter -- Bob Dylan or Taylor Swift (according to a large language model)

Advanced Transcript: Interview with Maya Rossin-Slater of Stanford University

This and That Causal Inference

Saturday links

ElectionGPT Predicts Harris to get between 306 and 316 electoral college votes (September 25th)

Update on ElectionGPT

S4E3: Mohammad Akbarpour, Microeconomic Theory, Stanford

Advanced Transcript: Interview with Mohammad Arkbarpour

Saturday links

Effect of AI on learning versus effect of AI on completed learning tasks

Strawberry Use Cases #1: Chain of Thought in Back-of-the-Envelope Math

Causal Inference Workshop and Causal AI

Closing my browser tabs

Does o1 engage in counterfeit reasoning and if so can we detect it?

ElectionGPT Update

S4E2: N. Greg Mankiw, Macroeconomics, Harvard

Next-Day Podcast Transcript: Interview with Dr. N. Greg Mankiw of Harvard University

Who Brings Potential Outcomes Notation Into Economics?

Saturday links

History of thought AI policies, AI assisted assignments, and final assignment connecting Princeton Industrial Relations Section with classical writers writing on labor

Children and Grandchildren of the Revolution: Part 2

Office Hours, Forward vs Reverse Causal Inference and Peter Hull's Design-Based Inference Workshop

Use Cases of ChatGPT-4o: Take me to the Iowa Writers Workshop

Closing my tabs

Update on ElectionGPT but first a story from ChatGPT

S4E1: Janet Currie, Health and Children, Princeton

Next-Day Podcast Transcript: Interview with Dr. Janet Currie of Princeton University

Closing my tabs

Narrative-Driven Predictions: Explaining Our ChatGPT-4o-mini Experiment in Election Forecasting

Mixtape Mailbag: When Firms Choose Their Own Treatments, Will That Violate Parallel Trends? Sometimes.

Pedro's DID Checklist: Step 4(i), more on selection

Closing my tabs

Children and Grandchildren of the Revolution: Part 1

Two Joke Tee Shirts and an AI Fueled Pet-Empathy Questionnaire

Does the PhD hurt mental health, how is it measured, is it selection? A little of all three

Orley Ashenfelter was the Father of the Revolution

Saturday links

Update to Podcast and Countdown to New Fall Mixtape Sessions Workshops

Mixtape Mailbag: Suggestions for Synthetic Control, as well as Callaway and Sant'Anna, on a Reader's Project with a Few Treated Units

Sunday links

119 Days Until the Mixtape Revision is Due

Side Effects, Partial Defiance, Partial Monotonicity Violation

New Agenda: Educating 1 million people in causal inference

Leaving the Basque Country, Almost Home

Lesser-Known Biases in Standard OLS Specifications for Difference-in-Differences with Covariates

S3E26: Javier Gardeazabal, Political Economy and Econometrics, University of the Basque Country

It's that time of year again: Mixtape Sessions Fall 2024 Lineup!

Saturday stuff: Random links, videos of me and my daughter in San Sebastián and updates about my podcast's subscription and download numbers

No Anticipation Violation, Conditional Parallel Trends, Heterogenous Treatment Effects with Ashenfelter's Dip? Pedro's Checklist, Step 4(h)

S3E25: Avinash K. Dixit, Microeconomics, Princeton University

"Just when I thought I was out, they pull me back in!" Step 4(g) of Pedro's Checklist: Ashenfelter's Dip with conditional parallel trends and heterogenous treatment effects

Saturday Links

Talking to People to Understand Selection is first best and if that still isn't enough, then I have some other suggestions: Step 4(f) of Pedro's Diff-in-diff Checklist (my last entry!)

Perfect Doctor Violates Parallel Trends: Step 4(e) in Pedro's DiD Checklist

S3E24: David Autor, Labor Economist, MIT

Personal Reflections: day one in San Sebastián, the Basque Country

Goodbye Scotland. Hello San Sebastian

Selection on observables, covariate-specific trends and conditional parallel trends with difference-in-differences: Pedro's Checklist, Step 4(d)

S3E23: Adriana Lleras-Muney, Labor Economist, UCLA

Last Saturday in Italy!

Pedro’s checklist 4c: Ashenfelter Dip, Parallel Trends but Non-zero Pre-trends

Step 4b of Pedro’s DID checklist: Difference-in-Differences, Selection Mechanisms and Parallel Trends After Earth's Great War

S3E22: Manisha Shah, Development Economist, UC Berkeley (episode 100!)

An amazing journey with Claude 3.5 and ChatGPT-4o who helped me backwards engineer an econometrics theory paper and taught me a lot more in the process

Saturday in Italy

Selection on Y(0) and Parallel Trends: Anticipating Step (4a) in Pedro's Diff-in-Diff Checklist

Step (3) in Pedro’s diff-in-diff checklist: plotting the outcome

(Repeat): S2:E1 Interview with Jeff Wooldridge, Economist and Econometrician

Step (2) of Pedro's DiD checklist: documenting how many units are in each cohort

My Review of the Apple Vision Pro After One Month

What Does Braveheart Have To Do With an Upcoming Workshop in Stirling, Scotland: July 1-4th? Everything

S3E21: Ashesh Rambachan, Predictive Algorithms and Causal Inference, MIT

Personal reflections: using chatgpt for personal growth, why I teach causal inference so much, and some updates on a new paper

Saturday Links

Pedro’s diff in diff checklist: step 1) plotting the rollout

Lalonde - 40 years later (Imbens and Xu's review): My First Impressions

S3E20: Henry Farber, Labor Economist, Princeton

Day one of selection on observables class at Collegio Carlo Alberto in Torino, some more food, and some other stuff.

Yummy and Inexpensive Food in Torino, Friends in Torino and my Mixtape Revision Summer Plans

Saturday links (Torino edition)

Leaving Madrid, Heading to Torino

CodeChella Madrid -- Initial Reflections

S3E19: Sarah Miller, Health Economist, Michigan

Saturday morning links

S3E18: E. Glen Weyl, Economist and Author, Microsoft

Saturday Links

ChatGPT-4o writes a causal inference exam with diff-in-diff, takes the exam, grades the exam, then grades the grading of the exam

S3E17: Matthew Jackson, Economics of Networks, Stanford

Saturday morning cleaning out my browser by sharing links and closing tabs

Using ChatGPT-4 to analyze my class evaluations

Why is TWFE biased in some event study graphs but not others? (with an Apple Vision Pro explainer at the end)

CodeChella Madrid, My Summer Plans in Europe, and a Video Review of my new Apple Vision Pro

S3E16: Bruce Sacerdote, Labor Economist, Dartmouth

Saturday morning links: scanning articles on the future of AI and society

The Pinocchio Effect, Economies of Scale and Market Concentration in AI

S3E15: Peter Boettke, Austrian Economics, George Mason University

The 2018 Farm Bill Apparently Legalized THC

Saturday morning links

Mixtape Book Sales

S3E14: Jesse Rothstein, Labor Economist, UC Berkeley

CAREER is a Transformer Model Used to Predict Occupational Outcomes

Introducing "Design-Based Regression Inference" Workshop Taught by Peter Hull

S3E13: Martin Gaynor, Health Economist, Carnegie Mellon/DOJ

ChatGPT Can Predict the Future When it Tells Stories Set in the Future About the Past

Saturday morning links

Validating Econometric Design: A Case Study from James Habyarimana's Updates to his 2003 Job Market Paper

Mental health needs among inmates and self harm attempts — my new paper just out in JHR

S3E12: Daniel Chen, Political Economy, Toulouse

Saturday morning links

Workshop Announcement, Regression Adjustment and Needing to Cite Packages else they become Public Goods

S3E11: Peter Klein, Entrepreneurship, Baylor

Saturday links

Mixtape Sessions: Past, Present and Future (maybe)

S3E10: Richard Blundell, Labor Economist, University of College London

[Reposting S1E14]: Interview with Petra Todd, Econometrician, University of Pennsylvania

Triple differences part 5: Presenting the event study plots

Saturday morning links

Another workshop announcement, heading to Houston and desiring a tribe

[Reposting] S1E27: Interview with Kyle Kretschman, head of economics at Spotify

Workshop announcement and getting back on track

Saturday links: Europe edition

Was Neyman's 1923 Potential Outcomes Notation Originally for Continuous Treatments?

S3E9: Pierre Chiappori, Micro Theorist, Columbia University

Saturday morning links with a lot of rambling thoughts while I should be packing for my trip to Germany

Generative AI and Worker Productivity

S3E8: Marianne Bitler, Public Economist, UC Davis

Last plug for Demand Estimation Workshop

Saturday links

Another workshop announcement: diff-in-diff

Workshop announcement: Difference-in-differences (Causal 2)

Workshop announcement: DEMAND ESTIMATION

S3E7: Wilbert van der Klaauw, Research Economist, NY Federal Reserve

Mixtape Mailbag #10: Letters from and to a Reader Contemplating Dropping Out of Their PhD Program

Saturday weekly links

Decomposing TWFE in a Continuous Diff-in-Diff: Part 1

Brief mention of continuous diff in diff

S3E6: Bruce Hansen, Econometrician, Univ of Wisconsin

Mixtape Mailbag #9: Log Transformations in Diff-in-Diff with Continuous Treatments

Saturday morning open tabs

S3E5: Chris Taber, Labor Economist, Wisconsin

Mixtape Mailbag #8: Continuous Triple Differences

It’s raining websites!

Using ChatGPT-4 for a new price discriminating hurdle for my workshops

Difference-in-Differences: No Anticipation with Parallel Trends (with a simulation and equations)

S3E4: Andrew Baker, Professor, UC Berkeley Law

Workshop announcement: Causal Inference 1

Saturday morning open tabs

Workshop announcement: $95 price for non-tenure track or professors with higher teaching loads

S3E3: Carlos Cinelli, Statistician, University of Washington

Mixtape Mailbag #7: What Happens in Difference-in-Differences if Parallel Trends is satisfied but No Anticipation is Violated?

Saturday roundup of open tabs

Labor's Design and the Making of Good Music

Redesigning my Causal Inference Class and a Sharing of my Worldview

S3E2: Caitlin Myers, Labor Economist, Middlebury College

Mixtape Mailbag #6: Redefining a diff-in-diff problem as a SUTVA violation

Using ChatGPT-4 to Decorate My Living Room

Workshop announcement: Causal I

Scientific Accuracy and Readability

Workshop announcement: demand estimation

S3E1: Richard Freeman, Labor Economist, Harvard

Mixtape Mailbag #5: My comments on a reader's paper using diff-in-diff to study a program's impact reducing violence against women

CodeChella Madrid 2024

Saturday morning weekly roundup

Penultimate day in Rome

Matrix Completion: Part 2

Matrix completion: Part 1

Visualizing your event study plot

Updates from Rome