A Prediction Model for Walkability Index Used by Urban Planners
Open Access DepositedIn the United States, nearly 40% of adults have obesity. The high prevalence has contributed a significant financial burden to the United States’ healthcare system, incurring over $173 billion in medical care expenses annually. The medical care of obese individuals costs $2,505 more than that of normal-weighted adults. A common preventable cause of obesity is physical inactivity. On a national level, only half of the population report meeting the federal recommendations for physical activity. The National Walkability Index is a widely recognized tool for examining walkability. It is based on the Environmental Protection Agency’s Smart Location Database and relies on the ranking of block groups. This method, however, limits the index’s applicability to an aggregated level and does not allow urban planners to predict walkability at smaller units of census geography. In this research, data reduction techniques and multiple regression and statistical analysis are used to identify and analyze significant factors that contribute to a composite walkability index. The new multiple regression model provides an independent tool for urban planners to predict walkability for any area, without being limited to block group units. The model can accurately predict a walkability index of a location with a mean absolute percentage error of 13.79%, a root mean square error of 1.31, and a relative root mean square error of 0.1373. The model also has a low standard deviation of 1.31 and a high r-square of 91.03%. Application of this tool can promote more walkable communities, leading to increased physical activity and subsequently reducing the financial burden of obesity on the United States’ healthcare system.
- All rights reserved
Notice to Authors
If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.