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

Popular guidance on observational data analysis states that outcomes shouldbe blinded when determining matching criteria or propensity scores. Such ablinding is informally said to maintain the "objectivity" of the analysis, andto prevent analysts from fishing for positive results by exploiting chanceimbalances. Contrary to this notion, we show that outcome blinding is not asufficient safeguard against fishing. Blinded and unblinded analysts canproduce bias of the same order of magnitude in cases where the outcomes can beapproximately predicted from baseline covariates. We illustrate thisvulnerability with a combination of analytical results and simulations.Finally, to show that outcome blinding is not necessary to prevent bias, weoutline an alternative sample partitioning procedure for estimating the averagetreatment effect on the controls, or the average treatment effect on thetreated. This procedure uses all of the the outcome data from all partitions inthe final analysis step, but does not require the analysis to not be fullyprespecified.

Treatment Effect Bias from Sample Snooping: Blinding Outcomes is Neither Necessary nor Sufficient