Below are the first 10 and last 10 pages of uncorrected machine-read text (when available) of this chapter, followed by the top 30 algorithmically extracted key phrases from the chapter as a whole.
Intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text on the opening pages of each chapter.
Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages.
Do not use for reproduction, copying, pasting, or reading; exclusively for search engines.
OCR for page 18
18 Guidebook for Conducting Airport User Surveys
from year to year. Some airports perform user surveys, particularly air passenger surveys, every
year. Others perform them much less frequently, perhaps every five years (Gosling and Maric,
2006). Airport user surveys performed by other organizations, such as metropolitan planning
organizations, are typically performed less frequently than every year. For example, the San Fran-
cisco Bay Area Metropolitan Transportation Commission has sponsored air passenger surveys
at the three Bay Area primary airports every five years. As a result, there is a fairly good histori-
cal record of long-term changes in market composition. However, significant changes can occur
over five years, as evidenced by the changes in the economy and the airline industry after Sep-
tember 2001. With surveys spread five years apart it is difficult to pick up recent trends or even
determine whether differences from one survey to the next are part of a longer-term trend or just
a feature of the specific year the survey was performed.
2.3.3 Dealing with Daily and Weekly Variability
User characteristics can also vary by time of day and day of week. Early morning and late after-
noon periods typically have more origin-destination passengers, while midday flights have more
connecting passengers. Morning flights tend to have more local residents, while afternoon flights
have more visitors. Weekday flights have more business passengers, while weekend flights have
more passengers traveling for personal reasons. Most departures from the U.S. West Coast to
Europe are in the late afternoon to evening, with the corresponding arrivals spread through the
afternoon. Therefore, it is desirable that the sampling period covers all hours of the day that flights
operate, over at least one complete week. If the survey is conducted for fewer than seven days, the
proportion of the target sample on weekdays and weekends should be set equal to the proportion
of passengers during those two periods. However, failure to provide survey coverage for some
hours or days will give results that are not completely representative of the target population,
because it will provide no information on the characteristics of airport users during those peri-
ods. While weighting of survey results can partially correct for known sample bias due to over-
sampling some periods (e.g., having more responses from passengers on a given day than the share
of the total weekly traffic on that day), there is no way to correct for the unknown bias due to not
sampling some periods.
2.3.4 Sample Size
While the issues of survey timing and frequency need to be decided on the basis of the survey
purpose, the particular data needs and the availability of resources, the issue of frequency is also
related to sample size. Conducting surveys with a smaller sample size several times each year may
produce better information for decision making and planning than conducting less frequent sur-
veys with a much larger sample size every few years, for much the same overall cost. The results
are likely to be more robust than those from a single survey of equivalent size conducted at a sin-
gle point in time, because the multiple survey waves will better reflect changes in traffic compo-
sition over time. The results of multiple survey waves over several years can always be combined
when a large sample is required to permit detailed analysis.
2.4 External Agencies
The results of an airport user survey are likely to be of interest to organizations other than the
survey sponsor. Other organizations may have information needs that could be met by expand-
ing the scope of a planned survey. For example, information on the use of ground transporta-
tion by travelers is likely to be of interest to regional transportation planning agencies as well as
public agencies and private-sector operators providing ground transportation services at the air-
