This skeet is in celebration of 75 years of Nash equilibrium.

At least, we can make the following interesting statement about zero-sum games but not about general games: “if there are two players, then there is a Nash equilibrium in minimax strategies.”

Yes, and I have difficulty reconciling the (strong) reading of Itai’s statement with the intuition that the class of all zero-sum games includes the class of two-player zero-sum games, and those are special.

bsky.app/profile/cfca...

I have exactly one paper that uses “unique”, and every use is in the mathematical sense.

Probably I overuse semicolons.

Look, if the WSJ could cluster their standard errors then all would be right in the world.

While we’re at it, can we have a ruling that the press can’t take a correlational study and assert causation by innuendo?

For what it’s worth, as a reader I’d really appreciate knowing how much was disclosed to the editorial team.

And it would give authors incentives to push for more transparency where feasible.

Thank you for shedding light on this!

Is there any way to know, by reading the published paper, whether the identity of the data source was available to the editors?

Our policy is already too long to cover all possible scenarios, I am told (repeatedly...), but it is very clear "access to the data and code is nonexclusive to the authors" in line 1 ... www.aeaweb.org/journals/dat... Need an exception? See line 3, and a discussion w/ editor + me ensues.

Thank you for doing this! (Is this policy public? It would be great if it were common knowledge.)

A sensible implementation would involve the editor contacting the company directly.