Diana M Thomas1, Nicholas Clark1, Dusty Turner1, Cynthia Siu2, Tanya M Halliday3, Bridget A Hannon4, Chanaka N Kahathuduwa5, Cynthia M Kroeger6,7, Roger Zoh8, David B Allison7. 1. Department of Mathematical Sciences, US Military Academy, West Point, NY, USA. 2. Department of Data Science, COS and Associates Ltd., Hong Kong, China. 3. Department of Health, Kinesiology, and Recreation, University of Utah, Salt Lake City, UT, USA. 4. Division of Nutritional Sciences, University of Illinois at Urbana-Champaign, Urbana, IL, USA. 5. Department of Human Development and Family Studies, Texas Tech University, Lubbock, TX, USA. 6. Charles Perkins Centre, School of Pharmacy, Faculty of Medicine and Health, University of Sydney, Sydney, Australia. 7. Department of Epidemiology and Biostatistics, Indiana University School of Public Health-Bloomington, Bloomington, IN, USA. 8. School of Public Health, Indiana University, Bloomington, IN, USA.
Abstract
BACKGROUND: Regression to the mean (RTM) is a statistical phenomenon where initial measurements of a variable in a nonrandom sample at the extreme ends of a distribution tend to be closer to the mean upon a second measurement. Unfortunately, failing to account for the effects of RTM can lead to incorrect conclusions on the observed mean difference between the 2 repeated measurements in a nonrandom sample that is preferentially selected for deviating from the population mean of the measured variable in a particular direction. Study designs that are susceptible to misattributing RTM as intervention effects have been prevalent in nutrition and obesity research. This field often conducts secondary analyses of existing intervention data or evaluates intervention effects in those most at risk (i.e., those with observations at the extreme ends of a distribution). OBJECTIVES: To provide best practices to avoid unsubstantiated conclusions as a result of ignoring RTM in nutrition and obesity research. METHODS: We outlined best practices for identifying whether RTM is likely to be leading to biased inferences, using a flowchart that is available as a web-based app at https://dustyturner.shinyapps.io/DecisionTreeMeanRegression/. We also provided multiple methods to quantify the degree of RTM. RESULTS: Investigators can adjust analyses to include the RTM effect, thereby plausibly removing its biasing influence on estimating the true intervention effect. CONCLUSIONS: The identification of RTM and implementation of proper statistical practices will help advance the field by improving scientific rigor and the accuracy of conclusions. This trial was registered at clinicaltrials.gov as NCT00427193. Published by Oxford University Press on behalf of the American Society for Nutrition 2019.
BACKGROUND: Regression to the mean (RTM) is a statistical phenomenon where initial measurements of a variable in a nonrandom sample at the extreme ends of a distribution tend to be closer to the mean upon a second measurement. Unfortunately, failing to account for the effects of RTM can lead to incorrect conclusions on the observed mean difference between the 2 repeated measurements in a nonrandom sample that is preferentially selected for deviating from the population mean of the measured variable in a particular direction. Study designs that are susceptible to misattributing RTM as intervention effects have been prevalent in nutrition and obesity research. This field often conducts secondary analyses of existing intervention data or evaluates intervention effects in those most at risk (i.e., those with observations at the extreme ends of a distribution). OBJECTIVES: To provide best practices to avoid unsubstantiated conclusions as a result of ignoring RTM in nutrition and obesity research. METHODS: We outlined best practices for identifying whether RTM is likely to be leading to biased inferences, using a flowchart that is available as a web-based app at https://dustyturner.shinyapps.io/DecisionTreeMeanRegression/. We also provided multiple methods to quantify the degree of RTM. RESULTS: Investigators can adjust analyses to include the RTM effect, thereby plausibly removing its biasing influence on estimating the true intervention effect. CONCLUSIONS: The identification of RTM and implementation of proper statistical practices will help advance the field by improving scientific rigor and the accuracy of conclusions. This trial was registered at clinicaltrials.gov as NCT00427193. Published by Oxford University Press on behalf of the American Society for Nutrition 2019.
Entities:
Keywords:
nutrition and obesity research; regression to the mean; statistical errors; treatment effect; unsupported conclusions
Authors: Brandon J George; T Mark Beasley; Andrew W Brown; John Dawson; Rositsa Dimova; Jasmin Divers; TaShauna U Goldsby; Moonseong Heo; Kathryn A Kaiser; Scott W Keith; Mimi Y Kim; Peng Li; Tapan Mehta; J Michael Oakes; Asheley Skinner; Elizabeth Stuart; David B Allison Journal: Obesity (Silver Spring) Date: 2016-04 Impact factor: 5.002
Authors: Paul T Akins; Maria Cs Inacio; Johannas A Bernbeck; Jessica Harris; Yuexin X Chen; Heather A Prentice; Kern H Guppy Journal: Spine (Phila Pa 1976) Date: 2018-01-01 Impact factor: 3.468
Authors: Asheley Cockrell Skinner; Steven B Heymsfield; Angelo Pietrobelli; Myles S Faith; David B Allison Journal: Int J Behav Nutr Phys Act Date: 2015-05-07 Impact factor: 6.457
Authors: Sagun Agrawal; Alexis C Wojtanowski; Laura Tringali; Gary D Foster; Eric A Finkelstein Journal: PLoS One Date: 2021-02-11 Impact factor: 3.240
Authors: Kelsey M Cochrane; Brock A Williams; Jordie A J Fischer; Kaitlyn L I Samson; Lulu X Pei; Crystal D Karakochuk Journal: Curr Dev Nutr Date: 2020-09-24
Authors: Danny Valdez; Colby J Vorland; Andrew W Brown; Evan Mayo-Wilson; Justin Otten; Richard Ball; Sean Grant; Rachel Levy; Dubravka Svetina Valdivia; David B Allison Journal: F1000Res Date: 2020-10-14
Authors: Chwan-Li Shen; Bruce A Watkins; Chanaka Kahathuduwa; Ming-Chien Chyu; Masoud Zabet-Moghaddam; Moamen M Elmassry; Hui-Ying Luk; Jean-Michel Brismée; Ami Knox; Jaehoon Lee; Mimi Zumwalt; Rui Wang; Tor D Wager; Volker Neugebauer Journal: Front Med (Lausanne) Date: 2022-01-03