Instrumental variable methods for a binary outcome were used to informatively address non-compliance in a randomised trial in surgery

Randomisation can be used as an instrumental variable (IV) to account for unmeasured confounding when seeking to assess the impact of non-compliance with treatment allocation in a randomised trial. We present and compare different methods to calculate the treatment effect on a binary outcome as a rate ratio in a randomised surgical trial.

from ! ORL Sfakianakis via paythelady.61 on Inoreader http://ift.tt/2hN8LQS
via IFTTT