1/ Agent-based models for simulating token design.https://twitter.com/laurashin/status/1140986942928097280 …
-
-
4/ Now, ABMs are growing popular again. They're useful and computing power is high enough now. But, I'm really enjoying the idea of a resurgence in ABM popularity after over promising too much... ...coming from crypto-world post their bullshit brush clearing fire.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I was super excited about them before grad school. It felt like such a cool idea that you could study people by programming their behaviors and interactions. My theory is that increasingly available large scale online data was a strong substitute.
-
The tl;dr on agent-based and other simulation models, at least for
#causalinference, is that for each piece of individual-level data you replace with an assumption (including group-level rates, probs, etc), you need to also add add’l causal assumptions or you’ll get bias. - 2 more replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.