Incorrect Analyses of Cluster-Randomized Trials that Do Not Take Clustering and Nesting into Account Likely Lead to p -Values that Are Too Small

Abstract

Get full access to this article

View all access options for this article.

References

Aceves-Martins

, Llauradó

, Tarro

, et al. A school-based, peer-led, social marketing intervention to engage spanish adolescents in a healthy lifestyle (“We Are Cool”—Som la Pera Study): A parallel-cluster randomized controlled study. Child Obes, 2017; 13:300–313.

Casazza

, Allison

. Stagnation in the clinical, community and public health domain of obesity: The need for probative research. Clin Obes, 2012; 2:83–85.

Wood

, Wren

, Allison

. The need for greater rigor in childhood nutrition and obesity research. JAMA Pediatr, 2019; 173:311–312.

ClinicalTrials.gov Identifier: NCT02157402. EYTO (European Youth Tackling Obesity): A Randomized Controlled Trial in Catalonia (Spain) (EYTO-SPAIN). [Clinical trial]. 2014. Available at https://clinicaltrials.gov/ct2/show/NCT02157402 Last accessed June 4, 2019.

Llauradó

, Aceves-Martins

, Tarro

, et al. A youth-led social marketing intervention to encourage healthy lifestyles, the EYTO (European Youth Tackling Obesity) project: A cluster randomised controlled0 trial in Catalonia, Spain. BMC Public Health, 2015; 15:607.

National Institutes of

Health

. Research Methods

Resources

, Group- or Cluster-Randomized Trials (GRTs). [Research Methods

Resources].

2018. Available at https://researchmethodsresources.nih.gov/grt.aspx Last accessed June 4, 2019.

Oakes

, Kaufman

. Methods in Social Epidemiology. San Francisco, CA: John Wiley & Sons, 2017.

Campell

, Piaggio

, Elbourne

, et al. Consort 2010 statement: Extension to cluster randomised trials. BMJ, 2012; 345:e5661.

Gray

, Burgermaster

, Tipton

, et al. Intraclass correlation coefficients for obesity indicators and energy balance-related behaviors among New York city public elementary schools. Health Educ Behav, 2016; 43:172–181.

10.

Masood

, Reidpath

. Intraclass correlation and design effect in BMI, physical activity and diet: A cross-sectional study of 56 countries. BMJ Open, 2016; 6:e008173.

11.

Hedges

LV.

Correcting a significance test for clustering. J Educ Behav Stat, 2007; 32:151–179.

12.

VanHoudnos

, Greenhouse

. On the hedges correction for a t-test. J Educ Behav Stat, 2016; 41:392–419.