Citation

Fasihozaman Langerudi M, Abolfazl Kouros M, Sriraj PS. J. Transp. Health 2015; 2(2): 127-134.

Copyright

(Copyright © 2015, Elsevier Publishing)

DOI

10.1016/j.jth.2014.08.005

PMID

unavailable

Abstract

Public health, as a major factor influencing the livability and well-being of a community has been a subject of interest in many academic fields. It is postulated that public health has strong correlations with various factors including land development, urban form, and transportation system elements. However, due to scarcity of individual level and confidential health data, such analysis has been typically conducted in an aggregate level resulting in less accurate results due to aggregation bias. In this paper, a methodology is developed and applied to disaggregate an individual-level health data in county scale into smaller geography by using an iterative proportional fitting approach while maintaining the marginal distributions of the controlled variables. Then, the disaggregated data is used to estimate various models of individual health condition as a function of socio-demographic, built environment, and transportation system attributes. It is noteworthy that the proposed approach can be applied to disaggregate any aggregate data in an efficient way.

Language: en