Redefining standards for body mass index of the US population based on BRFSS data using mixtures

Using body mass index (BMI) data from 2012 Behavioral Risk Factor Surveillance System, we test a spectrum of single parametric skewed distributions as well as Gaussian mixture densities to determine best distributional fit. We find that a k-component Gaussian mixture is the best model to describe the distribution of BMI data for the overall US population and for the population divided by gender, race, and region. A 4-component Gaussian mixture with the following sub-population means (standard deviations) fits best the US population: $ 22.21(\sigma =2.27) $ 22.21(σ=2.27), $ 26.05(\sigma =2.19) $ 26.05(σ=2.19), $ 29.83(\sigma =3.90) $ 29.83(σ=3.90), $ 35.47(\sigma =8.45) $ 35.47(σ=8.45) with corresponding weights: 23%, 25%, 37%, and 15%. Current obesity standards are set based on a convention and they are fairly dated. Overweight population has BMI (25.0, 29.9). Obese population is subdivided into three grades based on BMI: grade 1 (30–35), grade 2 (35–40), grade 3 (40 and above). Our study shows that modeling BMI using mixtures can be used to redefine current standards and support them with actual prevalence rather than a dated convention. By redefining BMI standards and employing the mixture models by gender and race, health and food policy makers will have opportunity to diversify policies and treatments of obesity as premier public health problem in the USA.