Any sample survey design involves a trade-off between funds available, sample size desired, and degree of precision required. Early in 1986, the northern virginia transportation commission sponsored aresearch project in northern virginia conducted by robert hitlin research associates, inc., And sg associates, inc., To estimate demandfor two proposed transit services. The two companies developed an estimation technique based on door-to-door sample surveys and small-scale telephone surveys. In this paper, the costs, findings, and advantages and disadvantages of the two types of data collection are compared. The telephone survey was approximately three and one-half times as expensive per interview as the door-to-door survey, but the results of the two surveys were virtually identical in each location. There were major differences in ease of administration, speed, required personnel, and other factors that may determine which approach to use in the future. A self-administered, door-to-door survey with alarge enough sample size to allow analysis at the subarea level andtherefore in narrow confidence intervals, which costs considerably less than a telephone survey is a cost-effective and viable option. This paper appeared in transportation research record no. 1144, Transit management, marketing, and performance. For covering abstract see IRRD no 818469.
Samenvatting