See original letter by Dagenais et al
Dr van Dongen-Boomsma Replies
To the Editor: My colleagues and I thank Dagenais and colleagues for their detailed letter, in which they ask for clarification of the following statement: "Post hoc, our sample had 80% power to detect a treatment effect of 0.90 . . . it is unlikely that our negative results were due to limited statistical power."1(826) Hopefully, this letter will answer their questions.
First, we appreciate Dagenais and colleagues’ acknowledgment regarding the robust methodological design of our study. Further, we thank them for pointing out an error in the text. Although we actually did have an 80% power to detect a treatment effect of 0.90, the power to detect rather small differences between EEG neurofeedback and placebo neurofeedback indeed was much more limited, namely between 5% and 11%, as they show. Thus, our statement "it is unlikely that our negative results were due to limited statistical power" was wrong. In other words, only a substantially larger sample size would have had enough power to establish such small effect sizes. However, it is questionable whether such small treatment effects would be clinically relevant and meaningful.
To overcome the power problem, future research demands larger samples and an even more robust design than our study. Therefore, it is a pleasure that the near future will bring such studies, as discussed by Kerson and the Collaborative Neurofeedback Group.2
References
1. van Dongen-Boomsma M, Vollebregt MA, Slaats-Willemse D, et al. A randomized placebo-controlled trial of electroencephalographic (EEG) neurofeedback in children with attention-deficit/hyperactivity disorder. J Clin Psychiatry. 2013;74(8):821-827. PubMed doi:10.4088/JCP.12m08321
2. Kerson C; Collaborative Neurofeedback Group. A proposed multisite double-blind randomized clinical trial of neurofeedback for ADHD: need, rationale, and strategy. J Atten Disord. 2013;17(5):420-436. PubMed doi:10.1177/1087054713482580
Author affiliation: Karakter Child and Adolescent Psychiatry University Centre, Nijmegen, The Netherlands.
Potential conflicts of interest: None reported.
Funding/support: None reported.
J Clin Psychiatry 2014;75(7):779 (doi:10.4088/JCP.14lr09043a).
© Copyright 2014 Physicians Postgraduate Press, Inc.
