Naïve regression requires weaker assumptions than factor models to adjust for multiple cause confounding.

Justin Grimmer Dean Knox Brandon M. Stewart Naïve regression requires weaker assumptions than factor models to adjust for multiple cause confounding. 2020 abs/2007.12702 CoRR https://arxiv.org/abs/2007.12702 db/journals/corr/corr2007.html#abs-2007-12702