Andy Garin @andy_garin

Economist, interested in making work work for workers. Assistant Professor at Carnegie Mellon University, Heinz College. andygarin.com Joined March 2012

Tweets

6K
Followers

2K
Following

854
Likes

13K

Andy Garin @andy_garin

2 weeks ago

@hagertynw When I saw the original paper first presented, my initial reaction was “oh yeah, of course there is no way *these* guys are biased so let’s take this at face value 🙃”

0 0 3 299 0

View Details

Andy Garin @andy_garin

3 weeks ago

@ElioNimier @QJEHarvard Congrats!!

0 0 1 209 0

View Details

It's true that unemployment has gone up for recent college graduates. Many are concerned that AI is doing this. But how then do you explain the simultaneous rise in teenager unemployment? They work in restaurants and ice cream shops. Does that sound like AI? agglomerations.eig.org/p/smells-like-…

18 21 94 8K 20

View Details

Andy Garin @andy_garin

3 weeks ago

@ModeledBehavior Angling hard for that endorsement

0 0 1 364 0

View Details

Andy Garin @andy_garin

a month ago

@economoser @JohnsHopkins @Francesco_Bia Wow, congrats!!

0 0 2 159 0

View Details

Andy Garin @andy_garin

2 months ago

@economoser @JSchreger Congrats!!

1 0 1 143 0

View Details

Andy Garin @andy_garin

2 months ago

@BrendanDMoore @nd_econ Congrats!!

0 0 1 73 0

View Details

Andy Garin @andy_garin

2 months ago

@JonSteinsson Interesting! Very related to the forthcoming REStud by @DanieliOren dropbox.com/scl/fi/i6lpe74…

0 0 3 887 1

View Details

Andy Garin @andy_garin

2 months ago

@daniela_vidart @nberpubs Congrats!

1 0 1 166 0

View Details

Andy Garin @andy_garin

2 months ago

@instrumenthull You were born ready for this moment. So proud.

0 0 1 371 0

View Details

J Street @jstreetdotorg

3 months ago

After a violent settler attack, an Israeli rabbi visited a Palestinian community and heard testimony of men beaten while bound and families terrorized. “When they saw us they recoiled in fear at the kippot on our heads.” That should stop us in our tracks. Our Jewish values call on us to demand better than this.

Smol Emuni US @SmolEmuniUS

3 months ago

Yesterday, Rabbi Yehuda Gilad from ישיבת מעלה גלבוע visited the West Bank and wrote the statement below (provided in our translation): “With God’s help, Rosh Chodesh Nisan, ‘a time of atonement for all their generations.’ Yesterday, I went through a difficult and deeply

4 21 69 22K 17

6 41 158 18K 15

View Details

Dana Milbank @Milbank

3 months ago

I am leaving the Washington Post to join a new journalistic venture backed by Politico founder Robert Allbritton that will be both the hometown publication the D.C. region sorely needs and a scrappy and fearless national news organization. I hope you'll join us.

599 3K 13K 1.3M 626

View Details

Andy Garin @andy_garin

3 months ago

@causalinf @PhillipsEcon Noted and appreciated. Just wanted to be clear that while I tend towards skepticism I am *not* trying to blindly dismiss these approaches wholesale.

1 0 2 57 0

View Details

Andy Garin @andy_garin

3 months ago

@causalinf @PhillipsEcon Sure, but this is very clearly not what I said. You don’t have to agree, but I want to be clear you are not correctly representing my point.

1 0 0 24 0

View Details

Andy Garin @andy_garin

3 months ago

@causalinf @PhillipsEcon Sorry, it sounds like we’re arguing past each other because I explicitly said it could so long as it is justified by the context. You’re making it sounds like I’m rejecting it on vibes, which is the opposite of what I said. I say we shouldn’t be selling it on vibes alone.

0 0 0 17 0

View Details

Andy Garin @andy_garin

3 months ago

@causalinf @PhillipsEcon If there’s a specific reason to believe matching on certain controls satisfies a CIA or conditional PT assumption, that’s great an justifies these approaches. But I know very few people who are convinced by “I matched on some controls I have so this is better”

2 0 0 48 0

View Details

Andy Garin @andy_garin

3 months ago

@causalinf @PhillipsEcon Assumptions need to be based on an argument about institutions and how the world actually works. Conditioning on covariates is not a weaker assumption—it’s a *different* assumption that needs to be justified based on knowledge of the data generating process.

1 0 0 45 0

View Details

Andy Garin @andy_garin

3 months ago

@PhillipsEcon @causalinf I got what you were going for 😉

0 0 1 18 0

View Details

Andy Garin @andy_garin

3 months ago

@causalinf @PhillipsEcon I’m mainly saying that if one does not buy into matching strategies, it’s hard to imagine a case where one would believe causal estimates from DD with covariates. It’s hard to think of cases where relaxing from CIA to conditional PT makes for convincing identification

3 0 1 72 0

View Details

Andy Garin @andy_garin

3 months ago

@causalinf @PhillipsEcon By the same token, though, PT with covariates is an assumption that is barely weaker than selection on observables! If we don’t believe the unconditional PT assumption, do we ever really think it’s worth bothering with DinD?