English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Inferring causal effects of a treatment, intervention or policy fromobservational data is central to many applications. However, state-of-the-artmethods for causal inference seldom consider the possibility that covariateshave missing values, which is ubiquitous in many real-world analyses. Missingdata greatly complicate causal inference procedures as they require an adaptedunconfoundedness hypothesis which can be difficult to justify in practice. Wecircumvent this issue by considering latent confounders whose distribution islearned through variational autoencoders adapted to missing values. They can beused either as a pre-processing step prior to causal inference but we alsosuggest to embed them in a multiple imputation strategy to take into accountthe variability due to missing values. Numerical experiments demonstrate theeffectiveness of the proposed methodology especially for non-linear modelscompared to competitors.

MissDeepCausal: Causal Inference from Incomplete Data Using Deep Latent Variable Models