Related Experiment Video
Updated: Jul 1, 2026

Characterization of Complex Systems Using the Design of Experiments Approach: Transient Protein Expression in Tobacco as a Case Study
Published on: January 31, 2014
Identifying the best FDA-endorsed healthy label designs through best-worst scaling experiment
Jianhui Liu1, Bachir Kassas1, John Lai1
1University of Florida, Gainesville, FL, USA.
Objective:
This study aims to assess consumer preferences for fifteen proposed front-of-package 'Healthy' label candidates under the Food and Drug Administration's (FDA) of the US updated guidelines for the 'Healthy' label. The goal of this study is to identify which label designs best align with consumer preferences, thereby supporting the FDA's efforts to promote healthier dietary choices through effective labelling.
Design:
A best-worst scaling (BWS) experiment was conducted using a balanced incomplete block design to assess consumer preferences for the fifteen FDA-proposed 'Healthy' labels. Participants completed fifteen best-worst scaling choice tasks where they identified the 'best' and 'worst' design from three randomly presented options in each task.
Setting:
The experiment was conducted in a controlled laboratory setting in the USA.
Participants:
Three hundred and eight US adult consumers who are primary household shoppers without dietary restrictions.
Results:
Results from the random parameter logit model indicate that labels 12 and 8 emerged as the most preferred designs, with preference shares of 16·7 and 16·1 %, respectively. These two labels featured a prominent 'Healthy' display with bold blue font, balanced colour themes and check marks, which likely contributed to their appeal. The Krinsky and Robb bootstrapping method confirmed the statistical significance of the preferences for these labels over others.
Conclusions:
This study identifies two labels as the most preferred FDA-proposed 'Healthy' label designs, offering clear guidance to policymakers on effective labelling strategies. By adopting a consumer-preferred design, the FDA's 'Healthy' label may have greater potential to influence healthier food choices.
More Related Videos
Related Concept Videos
Factorial Design
Testing a Claim about Standard Deviation
The hypothesis testing for the claim of population standard deviation (or variance) requires the data and samples to be random and unbiased. The population distribution also must be normal. There is no specific requirement on the sample size as the estimation is based on the chi-square distribution.
As a first step, the hypothesis (null and alternative) concerning the claim about...
Bioequivalence Experimental Study Designs: Completely Randomized and Randomized Block Designs
Bioequivalence Experimental Study Designs: Repeated Measures, Cross-Over, Carry-Over, and Latin Square Designs
Study Designs in Epidemiology
Observational studies are those where the researcher does not intervene but rather observes natural variations. They include cross-sectional, cohort, and case-control studies.
Methods of Medium Optimization

