Local causal network learning for finding pairs of total and direct effects

Yue Liu, Zhuangyan Fang, Yangbo He, Zhi Geng, Chunchen LIU

Abstract:

In observational studies, it is important to evaluate not only the total effect but also the
direct and indirect effects of a treatment variable on a response variable. In terms of local
structural learning of causal networks, we try to find all possible pairs of total and direct
causal effects, which can further be used to calculate indirect causal effects. An intuitive
global learning approach is first to find an essential graph over all variables representing
all Markov equivalent causal networks, and then enumerate all equivalent networks and
estimate a pair of the total and direct effects for each of them. However, it could be
inefficient to learn an essential graph and enumerate equivalent networks when the true
causal graph is large. In this paper, we propose a local learning approach instead. In the
local learning approach, we first learn locally a chain component containing the treatment.
Then, if necessary, we learn locally a chain component containing the response. Next, we
locally enumerate all possible pairs of the treatment’s parents and the response’s parents.
Finally based on these pairs, we find all possible pairs of total and direct effects of the
treatment on the response.