Commentary: does the selective inversion approach demonstrate bias in the results of studies using routinely collected data?

Jonathan Sterne
2018 BMJ (Clinical Research Edition)  
General rights This document is made available in accordance with publisher policies. Please cite only the published version using the reference above. Full terms of use are available: Acknowledgement: This commentary draws on comments made by the late Professor Doug Altman, in his capacity as BMJ statistical editor. Standfirst: Selective inversion ("coining") of the direction of comparisons led to strong disagreements over the validity of a paper examining bias in studies of interventions
more » ... on routinely collected data, and a correction published in this week's BMJ.
doi:10.1136/bmj.k3259 pmid:30120090 fatcat:2nsh2cyw6jdlpdz7yglp5nrdxq