Supporting Parallel Trends (The Effect, Videos on Causality, Ep 54)

preview_player
Показать описание

The Effect is a book about research design and causal inference. How can we use data to learn about the world? How can we answer questions about whether X causes Y even if we can't run a randomized experiment? The book covers these things and plenty more. These videos are meant to accompany the book, although they can also be viewed on their own.

This video relates to material found in Chapter 18 of the book.

Parallel trends is a key assumption in doing a difference-in-differences analysis. How can we use data to check whether that assumption is plausible and can be trusted? This video goes through a few different ways.
  1. Econometrics, Causality, and Coding with Dr. HK
Рекомендации по теме
Supporting Parallel Trends 0:09:20

Supporting Parallel Trends (The Effect, Videos on Causality, Ep 54)

Parallel Trends (The 0:08:53

Parallel Trends (The Effect, Videos on Causality, Ep 52)

Introductory Stata 32: 0:02:34

Introductory Stata 32: DID Parallel Trend Assumption

14.5) Common Trend 0:02:06

14.5) Common Trend Assumption in Difference-in-Difference (DD) Estimator

Jonathan Roth 'Testing 1:32:28

Jonathan Roth 'Testing and Sensitivity Analysis for Parallel Trends'

9.3 - Difference-in-Differences 0:13:09

9.3 - Difference-in-Differences Assumptions and Proof

Econometrics - Difference 0:16:29

Econometrics - Difference in Differences

Luke Miratrix: A 1:02:18

Luke Miratrix: A devil’s bargain? Repairing a Diff-in-Diff parallel trends assumption with matching...

Lecture 38: Difference-in-Difference 0:26:13

Lecture 38: Difference-in-Difference Method (DID)

Optional Lecture 1. 0:22:30

Optional Lecture 1. Difference-in-differences

Data Science Research 0:45:52

Data Science Research Methods: Differences-in-differences estimation

Causal Inference -- 0:29:49

Causal Inference -- 19/23 -- Difference-in-Differences Examples

Andy Eggers, 'Placebo 0:58:51

Andy Eggers, 'Placebo Tests for Causal Inference'

John Gardner 'Two-stage 1:24:59

John Gardner 'Two-stage differences in differences'

Efficient Estimation for 1:11:00

Efficient Estimation for Staggered Rollout Design

Causal Inference -- 0:22:16

Causal Inference -- 17/23 -- Difference-in-Differences Basics I

Support Vector Machine 0:02:19

Support Vector Machine (SVM) in 2 minutes

Fitness Test 0:00:20

Fitness Test

Parallel Session 2 0:33:36

Parallel Session 2 - Future trends in Creative Tech (synthetic media, passion economy, FAST)

It's Not Manipulation, 0:10:57

It's Not Manipulation, It's Strategic Communication | Keisha Brewer | TEDxGeorgetown

Poverty Alleviation | 1:04:47

Poverty Alleviation | Parallel Session III | Path2Dev 2023

lenz's law #Short 0:00:53

lenz's law #Short

Parallel Session 4C: 1:28:50

Parallel Session 4C: Biodiversity Assesments: Scenarios, limits and implications

PMAP 8521 • 0:08:45

PMAP 8521 • Example: Diff-in-diff with R: 5: Diff-in-diff with regression

Комментарии
Автор

Thank you for the good video. I have a question.
In your model Y=intercept+ß1*Time++ß2*Time * Group + E. We have to test wheter ß2 is different from zero.
But how about a model in following set-up.
Y = intercept + ß1 * Group + ß2 * Time + ß3 * Group * Time + E.
Do I have to test (for parallel trend assumption), if ß1 differs from zero for the pre period?
I am a bit confused because to my understanding ß1 depicts the effect of an observation being part of the treatment group and if it differs from zero, than there are (significant) differences and PTA doesn´t hold. Am I rigth?
Very best regards!

schafer
Автор

Great video! Just had a question as to why we're only adding the group fixed effects when testing the parallel trends assumption and not year fixed effects as well, thanks!

samarth