Household travel surveys: Where are we going? Peter R. Stopher * , Stephen P. Greaves The Institute of Transport and Logistics Studies, The University of Sydney, NSW 2006, Australia Abstract In this paper, we commence by reviewing the recent history of household travel surveys. We note some of the problems that contemporary surveys are encountering throughout the world. We also review the data demands of current and emerging travel demand models, concluding that there are many new demands being placed on data, both in terms of the extent of the data required and the accuracy and completeness of the data. Noting that the standard method for con- ducting most household travel surveys is, and has been for some years, a diary, we briefly explore the evolution of the diary survey from the late 1970s to the present. In the next section of the paper, we explore a number of facets of potential future data collection. We include in this the use of GPS devices to measure travel, the potential of panel designs and some of the alternatives within panel designs, the development of continuous household travel surveys, especially in Australia, and the emerging capabilities in data fusion. Using some of these emerging methods for data collection and data simulation, we then propose a new paradigm for data collection that places the emphasis on a paid, national panel that is designed as a rotating, split panel, with the cross-sectional component conducted as a continuing survey. The basis of the panel data collection is proposed as GPS with demographic data, and the continuing national sample would also use GPS at its core. The potential to add in such specialised surveys as stated choice and process surveys is also noted as an advantage of the panel approach. We also explore briefly the notion that a special access panel or panels could be included as part of the design. Ó 2006 Elsevier Ltd. All rights reserved. Keywords: Data collection; Travel demand modelling; Panel surveys; Data fusion; GPS; Travel diaries 1. Introduction It is axiomatic that a model can never be better than the data from which it is estimated. In the early days of transport planning, large data sets were collected, using face-to-face home interviews, with sample sizes that were often as big as 1–3% of the population. Over the past 20 years, sample sizes have dropped considerably, and are more often now in the range of 2500–10,000 households, often representing much less than 1% of households in the region (Stopher and Metcalf, 1996; Cambridge Systematics, 1996), and surveys in North 0965-8564/$ - see front matter Ó 2006 Elsevier Ltd. All rights reserved. doi:10.1016/j.tra.2006.09.005 * Corresponding author. Tel.: +61 2 9351 0010; fax: +61 2 9351 0088. E-mail address: peters@itls.usyd.edu.au (P.R. Stopher). Transportation Research Part A 41 (2007) 367–381 www.elsevier.com/locate/tra