Estimating Potential Outcome Distributions with Collaborating Causal Networks. (arXiv:2110.01664v2 [stat.ML] UPDATED)

Web: http://arxiv.org/abs/2110.01664

Many causal inference approaches have focused on identifying an individual's
outcome change due to a potential treatment, or the individual treatment effect
(ITE), from observational studies. Rather than only estimating the ITE, we
propose Collaborating Causal Networks (CCN) to estimate the full potential
outcome distributions. This modification facilitates estimating the utility of
each treatment and allows for individual variation in utility functions (e.g.,
variability in risk tolerance). We show that CCN learns distributions that
asymptotically capture the correct potential outcome …

arxiv ml networks