@article{ref1,
title="Record linkage of crashes with injuries and medical cost in Puerto Rico",
journal="Transportation research record",
year="2020",
author="Bianchi Santiago, Josie D. and Colón Jordán, Héctor and Valdés, Didier",
volume="2674",
number="10",
pages="739-748",
abstract="Cost considerations are critical in the analysis and prevention of traffic crashes. Integration of cost data into crash datasets facilitates the crash-cost analyses with all their related attributes. It is, however, a challenging task because of the lack of availability of unique identifiers across the databases and because of privacy and confidentiality regulations. This study performed a record linkage comparison between the deterministic and probabilistic approaches using attributes matching techniques with numerical distance and weight patterns under the Fellegi-Sunter approach. As a result, the deterministic algorithm developed using the exact match of the 14-digit police accident record number had an overall matching performance of 52.38% of real matched records, while the probabilistic algorithm had an overall matching performance of 70.41% with a quality measurement of the sensitivity of 99.99%. The deterministic approach was thus outperformed by the probabilistic approach by approximately 20% of records matched. The probabilistic matching with numerical variables seems to be a good matching strategy supported by quality variables. On record matching, a multivariable regression model was developed to model medical costs and identify factors that increase the costs of treating injured claimants in Puerto Rico.<p /> <p>Language: en</p>",
language="en",
issn="0361-1981",
doi="10.1177/0361198120935439",
url="http://dx.doi.org/10.1177/0361198120935439"
}