Citation

Michos ED, Mitchell CM, Miller ER, Sternberg AL, Juraschek SP, Schrack JA, Szanton SL, Walston JD, Kalyani RR, Plante TB, Christenson RH, Shade D, Tonascia J, Roth DL, Appel LJ. Contemp. Clin. Trials 2020; ePub(ePub): ePub.

Affiliation

Department of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, United States; Welch Center for Prevention, Epidemiology, and Clinical Research, Johns Hopkins University, Baltimore, MD, United States; Division of General Internal Medicine, Johns Hopkins School of Medicine, Baltimore, MD, United States.

Copyright

(Copyright © 2020, Elsevier Publishing)

DOI

10.1016/j.cct.2020.105936

PMID

32001213

Abstract

We have identified two errors in our article:

1)
Misstatement of the primary analysis plan: the primary analysis plan is the intention-to-treat comparison of the pooled non-control doses group versus control with time to primary outcome measured from randomization for all participants, not the analysis which compares experience on best dose versus control dose. The primary analysis was stated correctly in our statistical analysis plan developed at the start of the trial. Importantly, this correction is not a protocol change; rather, the description of primary analysis in the design paper incorrectly stated what we had pre-specified in our statistical analysis plan.

2)
Inconsistent use of the term “best dose”: the “best dose” is the non-control dose identified during dose-finding stage as best at preventing the primary outcome; in some sentences, “best dose” was used incorrectly to denote the pooled non-control doses group.
We regret the confusion caused by our errors.

Language: en