A1 Journal article (refereed)
Causal Effect Identification from Multiple Incomplete Data Sources : A General Search-Based Approach (2021)

Tikka, S., Hyttinen, A., & Karvanen, J. (2021). Causal Effect Identification from Multiple Incomplete Data Sources : A General Search-Based Approach. Journal of Statistical Software, 99, Article 5. https://doi.org/10.18637/jss.v099.i05

JYU authors or editors

Publication details

All authors or editors: Tikka, Santtu; Hyttinen, Antti; Karvanen, Juha

Journal or series: Journal of Statistical Software

eISSN: 1548-7660

Publication year: 2021

Volume: 99

Article number: 5

Publisher: Foundation for Open Access Statistic

Publication country: Austria

Publication language: English

DOI: https://doi.org/10.18637/jss.v099.i05

Publication open access: Openly available

Publication channel open access: Open Access channel

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/78024

Publication is parallel published: https://arxiv.org/abs/1902.01073

Abstract

Causal effect identification considers whether an interventional probability distribution can be uniquely determined without parametric assumptions from measured source distributions and structural knowledge on the generating system. While complete graphical criteria and procedures exist for many identification problems, there are still challenging but important extensions that have not been considered in the literature such as combined transportability and selection bias, or multiple sources of selection bias. To tackle these new settings, we present a search algorithm directly over the rules of do-calculus. Due to the generality of do-calculus, the search is capable of taking more advanced datagenerating mechanisms into account along with an arbitrary type of both observational and experimental source distributions. The search is enhanced via a heuristic and search space reduction techniques. The approach, called do-search, is provably sound, and it is complete with respect to identifiability problems that have been shown to be completely characterized by do-calculus. When extended with additional rules, the search is capable of handling missing data problems as well. With the versatile search, we are able to approach new problems for which no other algorithmic solutions exist. We perform a systematic analysis of bivariate missing data problems and study causal inference under case-control design. We also present the R package dosearch that provides an interface for a C++ implementation of the search.

Keywords: causality; inference; search algorithms; R (programming languages); meta-analysis

Free keywords: causality; do-calculus; selection bias; transportability; missing data; case-control design; meta-analysis

Contributing organizations

Related projects

Ministry reporting: Yes

Reporting Year: 2021

JUFO rating: 1