Instrumental Variable-based Identification for Causal Effects using Covariate Information

Authors: Yuta Kawakami12131-12138

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper deals with the identification problem of causal effects in randomized trials with noncompliance. In this problem, generally, causal effects are not identifiable and thus have been evaluated under some strict assumptions, or through the bounds. Different from existing studies, we propose a novel identification condition of joint probabilities of potential outcomes, which allows us to derive a consistent estimator of the causal effect. Regarding the identification conditions of joint probabilities of potential outcomes, the assumptions of monotonicity (Pearl 2009), independence between potential outcomes (Robins and Richardson 2011), gain equality (Li and Pearl 2019) and specific functional relationships between cause and effect (Pearl 2009) have been utilized. In contrast, without such assumptions, the proposed condition enables us to evaluate joint probabilities of potential outcomes using an instrumental variable and a proxy variable of potential outcomes. The result of the present paper extends the range of solvable identification problems in causal inference.
Researcher Affiliation Academia Yuta Kawakami Department of Mathematics, Physics, Electrical Engineering and Computer Science Graduate School of Engineering Science, Yokohama National University 79-5 Tokiwadai, Hodogaya-ku, Yokohama 240-8501 JAPAN kawakami-yuta-yd@ynu.jp
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statements about open-sourcing code or links to a code repository.
Open Datasets No This is a theoretical paper focusing on identification conditions and does not describe or use any datasets for training or empirical evaluation.
Dataset Splits No This is a theoretical paper and does not involve dataset splits for validation or other purposes.
Hardware Specification No No experiments are conducted in this theoretical paper, and thus no hardware specifications are mentioned.
Software Dependencies No No experiments are conducted in this theoretical paper, and thus no software dependencies are listed.
Experiment Setup No No experiments are conducted in this theoretical paper, and thus no experimental setup details or hyperparameters are provided.