Data-Driven Causal Effect Estimation Based on Graphical Causal Modelling: A Survey

In many fields of scientific research and real-world applications, unbiased estimation of causal effects from non-experimental data is crucial for understanding the mechanism underlying the data and for decision-making on effective responses or interventions. A great deal of research has been conducted on this challenging problem from different angles. For causal effect estimation in data, assumptions such as Markov property, faithfulness and causal sufficiency are always made. Under the assumptions, full knowledge such as, a set of covariates or an underlying causal graph, is still required. A practical challenge is that in many applications, no such full knowledge or only some partial knowledge is available. In recent years, research has emerged to use a search strategy based on graphical causal modelling to discover useful knowledge from data for causal effect estimation, with some mild assumptions, and has shown promose in tackling the practical challenge. In this survey, we review the methods and focus on the challenges the data-driven methods face. We discuss the assumptions, strengths and limitations of the data-driven methods. We hope this review will motivate more researchers to design better data-driven methods based on graphical causal modelling for the challenging problem of causal effect estimation.