most citedNaïve regression requires weaker assumptions than factor models to adjust for multiple cause confounding

8 citations · 8 across the 1 of their papers we have counts for

collaborators

1 paper

stat.ME2020★ 8 cited

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

Justin Grimmer, Dean Knox, Brandon M. Stewart

The empirical practice of using factor models to adjust for shared, unobserved confounders, , in observational settings with multiple treatments, , is wides…