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

Randomization ensures that observed and unobserved covariates are balanced,on average. However, randomizing units to treatment and control often leads tocovariate imbalances in realization, and such imbalances can inflate thevariance of estimators of the treatment effect. One solution to this problem isrerandomization---an experimental design strategy that randomizes units untilsome balance criterion is fulfilled---which yields more precise estimators ofthe treatment effect if covariates are correlated with the outcome. Mostrerandomization schemes in the literature utilize the Mahalanobis distance,which may not be preferable when covariates are correlated or vary inimportance. As an alternative, we introduce an experimental design strategycalled ridge rerandomization, which utilizes a modified Mahalanobis distancethat addresses collinearities among covariates and automatically places ahierarchy of importance on the covariates according to their eigenstructure.This modified Mahalanobis distance has connections to principal components andthe Euclidean distance, and---to our knowledge---has remained unexplored. Weestablish several theoretical properties of this modified Mahalanobis distanceand our ridge rerandomization scheme. These results guarantee that ridgererandomization is preferable over randomization and suggest when ridgererandomization is preferable over standard rerandomization schemes. We alsoprovide simulation evidence that suggests that ridge rerandomization isparticularly preferable over typical rerandomization schemes inhigh-dimensional or high-collinearity settings.

Ridge Rerandomization: An Experimental Design Strategy in the Presence of Collinearity