Impact of Data Integration on Some Important Travel Behavior Indicators

Abstract

Travel surveys are one of the most important ways of obtaining the critical information needed for transportation planning and decision making today. Reliable and quality data from household travel surveys also demand large sample sizes. These surveys are notoriously expensive, however, and highly time-consuming, and they are faced with a high response burden and subsequent low response rates. Although methodological and technological survey techniques have become increasingly refined, high unit costs and public resistance will continue to plague future survey efforts. This paper investigates the impact of combining survey data from different sources on some important travel behavior indicators. Given the availability of other types of surveys such as time use surveys, which tend to collect a great deal of important data in regard to people's travel, a wealth of information can be obtained through combining these data with the available travel survey data. Initially, survey data were weighted on the basis of census data on some important socio-demographic characteristics that had been shown to have an impact on travel. Hereby, the fact that census data had the required sample size but generally did not have the required information on travel was exploited. The Flemish travel survey data were then combined with the Flemish time use survey data. The resultant combined data set offered a larger and more representative sample of the population, which gave more reliable travel information on the population. The larger sample was valuable in the prediction of travel demand and can also be used as a base for simulating travel data.