Determining the Relationship between U.S. County-Level Adult Obesity Rate and Multiple Risk Factors by PLS Regression and SVM Modeling Approaches

Abstract

Data from the Center for Disease Control (CDC) has shown that the obesity rate doubled among adults within the past two decades. This upsurge was the result of changes in human behavior and environment. Partial least squares (PLS) regression and support vector machine (SVM) models were conducted to determine the relationship between U.S. county-level adult obesity rate and multiple risk factors. The outcome variable was the adult obesity rate. The 23 risk factors were categorized into four domains of the social ecological model including biological/behavioral factor, socioeconomic status, food environment, and physical environment. Of the 23 risk factors related to adult obesity, the top eight significant risk factors with high normalized importance were identified including physical inactivity, natural amenity, percent of households receiving SNAP benefits, and percent of all restaurants being fast food. The study results were consistent with those in the literature. The study showed that adult obesity rate was influenced by biological/behavioral factor, socioeconomic status, food environment, and physical environment embedded in the social ecological theory. By analyzing multiple risk factors of obesity in the communities, may lead to the proposal of more comprehensive and integrated policies and intervention programs to solve the population-based problem.

Keywords

• Adult Obesity
• Food Environment
• PLS Regression
• SVM Model
• and Social Ecological Theory