Data Cleaning in Activity and Travel Surveys: A Methodology Applied to Walk Trips
Institute of Transportation Engineers Region X Student Conference
Activity-based household travel surveys are becoming much more common as states and metropolitan regions contemplate advancing their travel behavior forecasting abilities. Such activity and travel surveys are valuable for the estimation and calibration of activity-based travel demand forecasting models. Before travel survey records can be used, they must be edited using data cleaning processes that identify, reject, and/or correct internal inconsistencies, miscoded information, and other errors. Literature on travel survey data cleaning is sparse, and few travel survey data cleaning standards exist beyond ad-hoc rules of thumb. This paper presents a possible methodology for improving on data cleaning rules of thumb by borrowing statistical methods, especially from the field of robust statistics. The methodology was applied to the walk trip records of a household activity and travel survey conducted during 2011 in the Portland, Oregon, region. First, indicator variables were constructed to flag suspect walk trips. Next, visual inspection of the highest-ranking 5% of suspect walk trips was performed. The methodology identified 29 walk trips with an incorrect mode, 19 location errors, 39 trips with travel time errors, and 6 walk trips with inaccurate trip purposes. After correcting the mode errors and removing the trips with location errors, key walk calibration statistics were more reasonable, demonstrating the usefulness of a statistically-derived data cleaning methodology. Finally, the paper concludes with recommended foci for data cleaning efforts of activity-based household travel surveys.
Singleton, P. A. (2012 November). Data cleaning in activity and travel surveys: A methodology applied to walk trips. Presented at the Institute of Transportation Engineers Region X Student Conference, Portland, OR.