Andrew Grotzinger1, Tom Hildebrandt1, Jessica Yu1,2. 1. Eating and Weight Disorders Program, Department of Psychiatry, Icahn School of Medicine, New York, New York. 2. Department of Psychology, Rutgers, The State University of New Jersey, Piscataway, New Jersey.
Abstract
OBJECTIVE: Change in binge eating is typically a primary outcome for interventions targeting individuals with eating pathology. A range of statistical models exist to handle these types of frequency distributions, but little empirical evidence exists to guide the appropriate choice of statistical model. METHOD: Monte Carlo simulations were used to investigate the utility of semi-continuous models relative to continuous models in various situations relevant to binge eating treatment studies. RESULTS: Semi-continuous models yielded more accurate estimates of the population, while continuous models were higher powered when higher levels of missing data were present. DISCUSSION: The present findings generally support the use of semi-continuous models applied to binge eating data, with total sample sizes of roughly 200 being adequately powered to detect moderate treatment effects. However, models with a significant amount of missing data yielded more favorable power estimates for continuous models.
OBJECTIVE: Change in binge eating is typically a primary outcome for interventions targeting individuals with eating pathology. A range of statistical models exist to handle these types of frequency distributions, but little empirical evidence exists to guide the appropriate choice of statistical model. METHOD: Monte Carlo simulations were used to investigate the utility of semi-continuous models relative to continuous models in various situations relevant to binge eating treatment studies. RESULTS: Semi-continuous models yielded more accurate estimates of the population, while continuous models were higher powered when higher levels of missing data were present. DISCUSSION: The present findings generally support the use of semi-continuous models applied to binge eating data, with total sample sizes of roughly 200 being adequately powered to detect moderate treatment effects. However, models with a significant amount of missing data yielded more favorable power estimates for continuous models.
Authors: Christopher G Fairburn; W Stewart Agras; B Timothy Walsh; G Terence Wilson; Eric Stice Journal: Am J Psychiatry Date: 2004-12 Impact factor: 18.112
Authors: Susan L McElroy; James I Hudson; Julie A Capece; Karen Beyers; Alan C Fisher; Norman R Rosenthal Journal: Biol Psychiatry Date: 2007-01-29 Impact factor: 13.382
Authors: Silja Vocks; Brunna Tuschen-Caffier; Reinhard Pietrowsky; Stephan Jeff Rustenbach; Anette Kersting; Stephan Herpertz Journal: Int J Eat Disord Date: 2010-04 Impact factor: 4.861
Authors: Katherine Schaumberg; Erin E Reilly; Lisa M Anderson; Sasha Gorrell; Shirley B Wang; Margarita Sala Journal: Appetite Date: 2018-06-27 Impact factor: 3.868