Pataky, TC, Robinson, MA and Vanrenterghem, J (2017) A computational framework for estimating statistical power and planning hypothesis-driven experiments involving one-dimensional biomechanical continua. Journal of Biomechanics. ISSN 1873-2380
|
Text
Pataky2017-JournalOfBiomechanics-power.pdf - Accepted Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (1MB) | Preview |
Abstract
Statistical power assessment is an important component of hypothesis-driven research but until relatively recently (mid-1990s) no methods were available for assessing power in experiments involving continuum data and in particular those involving one-dimensional (1D) time series. The purpose of this study was to describe how continuum-level power analyses can be used to plan hypothesis-driven biomechanics experiments involving 1D data. In particular, we demonstrate how theory- and pilot-driven 1D effect modeling can be used for sample-size calculations for both single- and multi-subject experiments. For theory-driven power analysis we use the minimum jerk hypothesis and single-subject experiments involving straight-line, planar reaching. For pilot-driven power analysis we use a previously published knee kinematics dataset. Results show that powers on the order of 0.8 can be achieved with relatively small sample sizes, five and ten for within-subject minimum jerk analysis and between-subject knee kinematics, respectively. However, the appropriate sample size depends on a priori justifications of biomechanical meaning and effect size. The main advantage of the proposed technique is that it encourages a priori justification regarding the clinical and/or scientific meaning of particular 1D effects, thereby robustly structuring subsequent experimental inquiry. In short, it shifts focus from a search for significance to a search for non-rejectable hypotheses.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | 0903 Biomedical Engineering, 1106 Human Movement And Sports Science, 0913 Mechanical Engineering |
Subjects: | H Social Sciences > HA Statistics R Medicine > RC Internal medicine > RC1200 Sports Medicine |
Divisions: | Sport & Exercise Sciences |
Publisher: | Elsevier |
Related URLs: | |
Date Deposited: | 28 Nov 2017 11:04 |
Last Modified: | 04 Sep 2021 03:34 |
DOI or ID number: | 10.1016/j.jbiomech.2017.09.031 |
URI: | https://researchonline.ljmu.ac.uk/id/eprint/7610 |
View Item |