Answers are grounded in this paper and cite their sources.
Compares travel behavior metrics in US households using two survey frames, suggesting panel solutions may improve methodology.
This paper presents the results of a parallel sample frame test that was conducted as part of the 2022 National Household Travel Survey (NHTS) effort. Specifically, the United States Department of Transportation Federal Highway Administration (FHWA) fielded the 2022 NHTS using an address-based sample (ABS), which is state-of-the-practice in the US. At the same time, the FHWA fielded a parallel study using a probability-based panel frame sample (PFS). The two surveys were conducted by the same survey contractor, using the online survey program and protocols. After the surveys were completed, a separate firm conducted an independent evaluation. This evaluation was structured around components of Total Survey Error and in particular two aspects: sampling outcomes and differences in reported travel behavior. The evaluation revealed very few attributes that were meaningfully different between the two samples. Where differences were noted, they were primarily related to demographic attributes rather than travel-related attributes. These are particularly important findings given current trends in US survey research towards considering panel-based solutions as a means of combatting declining response rates and related increasing costs associated with fielding ABS surveys. The evaluation results suggest that the representativeness, statistical efficiency, and resulting travel behavior metrics of PFS show potential for use in US household travel surveys (cost is not considered in this evaluation).
No takes yet. Share an insight, caveat, or question.
Bricka et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: