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 clustered observational study (COS) design is the observational studycounterpart to the clustered randomized trial. In a COS, a treatment isassigned to intact groups, and all units within the group are exposed to thetreatment. However, the treatment is non-randomly assigned. COSs are common inboth education and health services research. In education, treatments may begiven to all students within some schools but withheld from all students inother schools. In health studies, treatments may be applied to clusters such ashospitals or groups of patients treated by the same physician. In thismanuscript, we study the identification of causal effects in clusteredobservational study designs. We focus on the prospect of differential selectionof units to clusters, which occurs when the units' cluster selections depend onthe clusters' treatment assignments. Extant work on COSs has made an implicitassumption that rules out the presence of differential selection. We derive theidentification results for designs with differential selection and thatcontexts with differential cluster selection require different adjustment setsthan standard designs. We outline estimators for designs with and withoutdifferential selection. Using a series of simulations, we outline the magnitudeof the bias that can occur with differential selection. We then present twoempirical applications focusing on the likelihood of differential selection.

Nonparametric identification of causal effects in clustered observational studies with differential selection