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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Most causal inference studies rely on the assumption of overlap to estimatepopulation or sample average causal effects. When data exhibit non-overlap,estimation of these estimands requires reliance on model specifications, due topoor data support. All existing methods to address non-overlap, such astrimming or down-weighting data in regions of poor support, change theestimand. In environmental health research, where study results are oftenintended to influence policy, changes in the estimand can diminish the study'simpact, because estimates may not be representative of effects in thepopulation of interest to policymakers. Researchers may be willing to makeadditional, minimal modeling assumptions in order to preserve the ability toestimate population average causal effects. We seek to make two contributionson this topic. First, we propose a flexible, data-driven definition ofpropensity score overlap and non-overlap regions. Second, we develop a novelBayesian framework to estimate population average causal effects with minormodel dependence and appropriately large uncertainties in the presence ofnon-overlap. In this approach, the tasks of estimating causal effects in theoverlap and non-overlap regions are delegated to two distinct models, suited tothe degree of data support in each region. Tree ensembles are used tonon-parametrically estimate individual causal effects in the overlap region,where the data can speak for themselves. In the non-overlap region, whereinsufficient data support means reliance on model specification is necessary,individual causal effects are estimated by extrapolating trends from theoverlap region via a spline model. The promising performance of our method isdemonstrated in simulations. Finally, we utilize our method to perform a novelinvestigation of the causal effect of natural gas compressor station exposureon cancer outcomes.

Estimating Population Average Causal Effects in the Presence of  Non-Overlap: The Effect of Natural Gas Compressor Station Exposure on Cancer  Mortality