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

The machine learning toolbox for estimation of heterogeneous treatmenteffects from observational data is expanding rapidly, yet many of itsalgorithms have been evaluated only on a very limited set of semi-syntheticbenchmark datasets. In this paper, we show that even in arguably the simplestsetting -- estimation under ignorability assumptions -- the results of suchempirical evaluations can be misleading if (i) the assumptions underlying thedata-generating mechanisms in benchmark datasets and (ii) their interplay withbaseline algorithms are inadequately discussed. We consider two popular machinelearning benchmark datasets for evaluation of heterogeneous treatment effectestimators -- the IHDP and ACIC2016 datasets -- in detail. We identify problemswith their current use and highlight that the inherent characteristics of thebenchmark datasets favor some algorithms over others -- a fact that is rarelyacknowledged but of immense relevance for interpretation of empirical results.We close by discussing implications and possible next steps.

Doing Great at Estimating CATE? On the Neglected Assumptions in Benchmark Comparisons of Treatment Effect Estimators