Citation

Yang Y, Sasaki K, Cheng L, Liu X. Transp. Res. D Trans. Environ. 2022; 110: e103405.

Copyright

(Copyright © 2022, Elsevier Publishing)

DOI

10.1016/j.trd.2022.103405

PMID

unavailable

Abstract

Although many studies have revealed the relationship between the built environment and active travel among older adults, limited studies offer insights into gender differences. Using data from Chiba (Japan), this study employs a random forest method to fill this gap by revealing the non-linear associations of the built environment with active travel time among older males and females, and adopts a Shapley Additive exPlanations method to interpret the models.

RESULTS show that: (1) The dominant contributions to active travel time are gendered. For example, distance to a cafe/pachinko contributes more to males' active travel time, while for females, population density contributes more. (2) The built environment attributes have non-linear associations with active travel time among older males and females. This, therefore, implies that built environment interventions are only effective to a certain extent. Implications of the findings offer nuanced guidance for a gender-equitable and age-friendly city.

Language: en

Keywords

Active travel; Built environment; Gender; Machine learning; Non-linear; Older adults