Economic Impact Analysis - Specific Issues - Data Collection
Methodology  -  Lake State Examples - Other Examples         
Back to Table of Contents                                                                                                   


Tian-Cole, S. 2005. "Comparing Mail and Web-Based Survey Distribution Methods: Results of Surveys to Leisure Travel Retailers." Journal of Travel Research 43(May):422-430.

This study compares responses from a Web-based survey and those from a pencil-and-paper survey in terms of response rates, data quality, demographic profiles of respondents, internal consistency of scales, and responses to items. Two samples from among the same population of the American Society of Travel Agents were randomly assigned to receive a questionnaire either by e-mail or by postal mail. Several differences were found between the Web-based survey and the paper-and-pencil survey. Response rates for the Web-base survey was lower and had more missing data fields than the mail survey. The two groups differed in 15.3% of the total items in the data set. The significantly different results from the two survey modes indicates that tourism researchers should consider including multiple data collection modes when studying the population.

Beaman, J. G., T.-C. Huan and J. P. Beaman. 2004. "Tourism Surveys: Sample Size, Accuracy, Reliability, and Acceptable Error." Journal of Travel Research 40(August):67-74.

This article attempts to clarify the use of survey terminology concerning survey accuracy and reliability in tourism research. The article suggests there is confusion about estimates being termed accurate, biased, being within a certain percentage, and being reproducible with an acceptable amount of error. The need for standards to assess accuracy is introduced. Statistical concepts that relate to understanding acceptable error are introduced using examples and graphics based on simulation. Variability in responses is documented using results from two large national surveys. Sample size to achieve particular levels of acceptable error for means, totals, and change/difference are determined graphically. Sample sizes are given for some values of acceptable error that estimate users might want.

Crompton, J. L. and S. Tian-Cole. 2001. "An Analysis of 13 Tourism Surveys: Are Three Waves of Data Collection Necessary?" Journal of Travel Research 39(May):356-368.

This study evaluates the effectiveness of using the three-wave approach to mail-based questionnaires. In the three-wave approach non-respondents are are sent two follow-up questionnaires. Taking results from 13 different studies that used this approach this study found that on 82% of the the variables tested across the data sets, the additions of waves 2 and 3 led to no change in the results, but a second wave typically reduced the variance on responses to the first wave by between 28% and 49%. The study found some empirical evidence that wave 2 and wave 3 respondents were unlike the first wave respondents, lending credence to the assertion that the three-wave approach increases the likelihood of obtaining information from all units chosen from a sampling population and decreases the likelihood of non-response bias. However, the authors maintain that a more cost-effective strategy may be to do away with the three-wave approach and do more intensive follow-up of smaller sampling of non-respondents.

Yuan, M. 2001. "Reoperationalizing Economic Data Collection." Annals of Tourism Research 28(3):727-737.

The purpose of this study is to investigate the differences between using a traditional survey design asking tourists to record their expenditures during the first two days of their trip in one area vs. using a new design that asks for only one day of expenditures for a pre-selected day of their trip. The results showed that the number of group expenditures and average daily expenditure did not differ significantly between the two treatment groups. However, the second approach did differ significantly in producing higher initial response rates, lower rejection rates and higher overall net response rates. While this methodology does work best with larger sample sizes, its higher usable response rate (12%) and potential cost savings may lead to the collection of better expenditure data, increased accuracy in forecasting and more effective long-term planning. Other studies should investigate other factors, such as modifying instruction or content, to aid researchers in designing methodologies that will produce the best results given cost limitations.

Breen, H., A. Bull and M. Walo. 2001. "A Comparison of Survey Methods to Estimate Visitor Expenditure at a Local Event." Tourism Management 22:473-479.

The paper investigate the relationship between recalled expenditure survey data and "social bravado" or peer pressure effects at special events. When using the interview recall technique, males had a tendency to overestimate their food and beverage expenditures when they were surveyed as part of a group. Other significant findings include that memory recall, rather than expenditure diaries, tended to result in lower estimation of visitor expenditures owning perhaps to memory decay. There were no differences in the reported expenditures from people who had their expenditure diary collected the last day of the event and those who mailed in their diary.

Ryan, C. and R. Garland. 1999. "The Use of a Specific Non-Response Option on Likert-type Scale." Tourism Management 20:107-113.

The paper argues that the use of non-response options in questionnaires relating to attitudinal research offers various advantages. First, if non-random patters of response on individual items within a questionnaire occur, such patterns may hold valuable information for the researcher. Second, the provision of the non-response option may mean that any resultant analysis is based upon a sample with appropriate knowledge or opinions, thereby aiding discrimination. To support this view, various pieces of past research by the authors are presented where patterns of non-response are analyzed. In each case it was found that the existence of the non-response option offered some new insight. Such insights could help to improve subsequent questionnaires, if used at the pilot study stage, or illustrate specific aspects of a sample's attitudes - for example, in one case, about uncertainty over a council's tourism policies.

Archer, B. H. 1996. "Economic Impact Analysis." Annals of Tourism Research 23(3):704-707.

This research notes describes the challenge with the paucity of data that exists for sound economic impact analysis with input-output models. While researchers are developing more and more elegant models, the adage of "garbage in, garbage out" very much applies. This challenge is often compounded at the local or regional level with the absence of any control total data. Very rarely do regional or local accounts exist. Researchers are compelled to undertake surveys and to use appropriate methods to "massage" or adapt the data to meet the requirements of the model. Provided that such "data treatment" is undertaken logically on a conceptual sound basis, it can fill the gaps where no other data exist.

Smith, S. L. J. 1995. Collecting Data on Tourism. In Tourism Analysis: A Handbook. Essex, Longman Group Limited. Second Edition: 42-63.

This chapter reviews how data are obtained for tourism analyses and it identifies three basic ways data is collected: observation, administrative record-keeping and surveys. Observation includes such things as observation the size of line ups or the time people spend in a museum exhibit. Administrative data are obtained in the course of routine business and include such things as visitor counts at the border, registration records or credit card records. The chapter focuses on the principles of and design of questionnaires. The principles reviewed include; format, confidentiality and anonymity, sample selection, and sample size. The design of effective questionnaires is also reviewed and deals with the topics of format, phrasing and content, question format and enhancing response rate.

Cannon, J. C. 1994. Issues in Sampling and Sample Design - A Management Perspective. Travel, Tourism, and Hospitality Research: A Handbook for Managers and Researchers. J. R. Brent Ritchie and Charles R. Goeldner (ed.), New York, John Wiley and Sons Ltd. Second Edition: 131-143.

This chapter briefly describes four basic sample methodologies: simple random sampling and systematic sampling; stratified random sampling; cluster sampling; and quota sampling. The advantages and disadvantages of each sampling technique is explored and explores the issues that should be considered when selecting a sample design. The chapter also includes various formulae for calculating sample errors.

Hurst, F. 1994. En Route Surveys. Travel, Tourism, and Hospitality Research: A Handbook for Managers and Researchers. J. R. Brent Ritchie and Charles R. Goeldner (ed.), New York, John Wiley and Sons Ltd., Second Edition: 453-471.

This chapter deals with the technique of en route surveys of tourists. An en route survey surveys visitors at various stages of their trips, while traveling with a particular mode of transit and while visiting attractions or at their place of accommodation. En route surveys are described as the most effective method for surveying tourists. Issues such as sample size, sampling error, bias, randomness and the style of questionnaire are also discussed. An example of en route survey used in the airline industry is examined in great detail.

Back to Table of Contents