Consequences of relying on statistical significance: some illustrations

ConclusionsResearchers and journals should abandon statistical significance as a pivotal element in most scientific publications. Confidence intervals around effect sizes are more informative, but should not merely be reported to comply with journal requirements.This article is protected by copyright. All rights reserved.

Source: European Journal of Clinical Investigation - February 1, 2018 Category: General Medicine Authors: Ben Van Calster, Ewout W Steyerberg, Gary S Collins, Tim Smits Tags: Methods Source Type: research