MissDeepCausal: Causal Inference from Incomplete Data Using Deep Latent Variable Models
This addresses a critical issue for researchers and practitioners in fields like healthcare or policy analysis where missing data is common, offering an incremental improvement over existing causal inference methods.
The paper tackled the problem of causal inference from observational data with missing covariates, which complicates standard methods, by proposing a method using deep latent variable models to learn latent confounders and incorporate them via multiple imputation, showing effectiveness in numerical experiments, especially for non-linear models.
Inferring causal effects of a treatment, intervention or policy from observational data is central to many applications. However, state-of-the-art methods for causal inference seldom consider the possibility that covariates have missing values, which is ubiquitous in many real-world analyses. Missing data greatly complicate causal inference procedures as they require an adapted unconfoundedness hypothesis which can be difficult to justify in practice. We circumvent this issue by considering latent confounders whose distribution is learned through variational autoencoders adapted to missing values. They can be used either as a pre-processing step prior to causal inference but we also suggest to embed them in a multiple imputation strategy to take into account the variability due to missing values. Numerical experiments demonstrate the effectiveness of the proposed methodology especially for non-linear models compared to competitors.