Journal Logo

SPECIAL COMMUNICATIONS: Invited Commentaries and Responses

Response

Schoenfeld, Brad J.; Contreras, Bret; Krieger, James; Grgic, Jozo; Delcastillo, Kenneth; Belliard, Ramon; Alto, Andrew

Author Information
Medicine & Science in Sports & Exercise: September 2019 - Volume 51 - Issue 9 - p 1972
doi: 10.1249/MSS.0000000000002000
  • Free

Dear Editor-in-Chief,

We thank Mr. Mizelman for his letter to the editor (1) and interest in our study (2). The author contends that the power analysis for our study was incorrect. We ran the power analysis using G*power, F tests for ANOVA with repeated measures, and within-between interaction. Note that our original statistical analysis was based on this statistical model; however, the reviewers of our article asked us to alter the method of analysis to an ANCOVA, and accordingly, we complied with their request. Below is the protocol of the power analysis as outputted from G*power, showing a required sample size of 36; thus, our methods were properly reported.

Input: Effect size f = 0.25

α err prob = 0.05

Power (1 − β err prob) = 0.80

Number of groups = 3

Number of measurements = 2

Corr among rep measures = 0.6

Nonsphericity correction ε = 1

Output: Noncentrality parameter λ = 11.2500000

Critical F = 3.2849177

Numerator df = 2.0000000

Denominator df = 33.0000000

Total sample size = 36

Actual power = 0.8256914

The author goes on to state that: “In addition, even if the a priori power analysis was correct, and the sample of n = 36 was sufficient for a power value of 0.8, the number of participants in the final analysis was smaller than 36 (n = 34) (1). As a result, power analysis of this final sample size, with the predetermined effect size of f = 0.25, results in even lower value of power, 0.218.” We agree that dropouts resulted in our study possibly being statistically underpowered. In fact, we were clear with this limitation as we mentioned in the Results section that, “Thus, the study was slightly underpowered based on initial power analysis,” and in the Limitations section, we mentioned that, “Fifth, the study had a relatively small sample size and thus may have been somewhat underpowered to detect significant changes between groups in certain outcomes.”

Brad J. Schoenfeld
Department of Health Sciences
CUNY Lehman College
Bronx, NY
Bret Contreras
Sport Performance Research Institute
AUT University, Auckland
NEW ZEALAND
James Krieger
Weightology, LLC
Redmond, WA
Jozo Grgic
Institute for Health and Sport (IHES)
Victoria University, Melbourne
AUSTRALIA
Kenneth Delcastillo
Ramon Belliard
Andrew Alto
Department of Health Sciences
CUNY Lehman College
Bronx, NY

REFERENCES

1. Mizelman E. Statistical power in a recent study by Schoenfeld et al. Med Sci Sports Exerc. 2019;51(9):1971.
2. Schoenfeld BJ, Contreras B, Krieger J, et al. Resistance training volume enhances muscle hypertrophy but not strength in trained men. Med Sci Sports Exerc. 2019;51(1):94–103.
Copyright © 2019 by the American College of Sports Medicine