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

Matching has become the mainstream in counterfactual inference, with whichselection bias between sample groups can be significantly eliminated. Howeverin practice, when estimating average treatment effect on the treated (ATT) viamatching, no matter which method, the trade-off between estimation accuracy andinformation loss constantly exist. Attempting to completely replace thematching process, this paper proposes the GAN-ATT estimator that integratesgenerative adversarial network (GAN) into counterfactual inference framework.Through GAN machine learning, the probability density functions (PDFs) ofsamples in both treatment group and control group can be approximated. Bydifferentiating conditional PDFs of the two groups with identical inputcondition, the conditional average treatment effect (CATE) can be estimated,and the ensemble average of corresponding CATEs over all treatment groupsamples is the estimate of ATT. Utilizing GAN-based infinite sampleaugmentations, problems in the case of insufficient samples or lack of commonsupport domains can be easily solved. Theoretically, when GAN could perfectlylearn the PDFs, our estimators can provide exact estimate of ATT.  To check the performance of the GAN-ATT estimator, three sets of data areused for ATT estimations: Two toy data sets with 1/2 dimensional covariateinputs and constant/covariate-dependent treatment effect are tested. Theestimates of GAN-ATT are proved close to the ground truth and are better thantraditional matching approaches; A real firm-level data set withhigh-dimensional input is tested and the applicability towards real data setsis evaluated by comparing matching approaches. Through the evidences obtainedfrom the three tests, we believe that the GAN-ATT estimator has significantadvantages over traditional matching methods in estimating ATT.

A Constructive GAN-based Approach to Exact Estimate Treatment Effect without Matching