Abstract
A proxy response is often accepted for household travel surveys to reduce the survey cost and increase the sample size, but proxy-response biases may be introduced into the sample data. To investigate and correct the bias, completer information for the survey is important, but such information is not always available in practice. This study proposes a novel model that can be applicable in situations where completer information is unavailable. The method introduces group-decision modeling in analyzing the response choices of the household travel survey, where the survey response is considered to be a task allocation among household members. The proposed model can infer the probability of proxy response and the proxy-response bias of trip-related records without completer information. The potential of the proposed model was confirmed by application to a household travel survey in Japan. The inferred probability of the proxy response and the inferred bias without completer data demonstrated surprisingly similar results to the existing study with actual proxy-response data. Specifically, the model inferred a high probability of proxy response in young adults and a low proxy probability in middle-aged females, and the model inferred the proxy-response bias that female proxy respondents in the middle-aged group report lower trip rates than self-respondents. This method will be valuable not only in travel surveys, but also in the general research and practice of social surveys.
Highlights
Social surveys, such as travel surveys, are conducted to obtain data for planning public policies, and high quality data is crucial
Transportation (2021) 48:283–302 biases exist, this study focuses on the proxyresponse bias in household travel surveys
Proxy response in household travel surveys can be defined as the situation in which a household member responds to a travel survey on behalf of the other members in the household
Summary
Social surveys, such as travel surveys, are conducted to obtain data for planning public policies, and high quality data is crucial. The mother in a household may report the estimated travel data of her entire household, which may include her father, husband, and children Her father may visit a hospital, walk to the park, or go to the community center, and the completer (mother) may not be aware of these trips. Several authors have investigated proxy-response bias using survey data with a special format to collect the completer information (Badoe and Steuart 2002; Richardson 2006; Wargelin and Kostyniuk 2006) They found trips were often underreported for individuals responding by proxy, which produced substantial bias in the travel survey data, so collecting information about the person responding by proxy is highly important.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
