Sinossi
Tourism studies often deal with complex mixes of external and local factors and the attitudes, perceptions and actions of tourists themselves. In seeking to understand individual elements of this mix, or the results of interactions between them, tourism authorities, managers and researchers often collect quantitative data, but until now the few existing guides to understanding quantitative data have been either very simple or very complicated. This book provides a guide to dealing with real-world data and goes beyond the methods usually covered in introductory textbooks. The first part considers key issues associated with using well known methods to produce valid and reliable models of real-world phenomena, emphasizing issues in data selection, approaches to factor and cluster analysis, and mathematical modelling using regression methods (including logistic regression) and structural equation modelling. The second part covers new approaches to modelling: maximum likelihood estimation, simulation and agent-based modelling. Each chapter includes extensive references to additional reading, and an appendix summarises the software introduced in the book. The book provides many practical examples of applications to tourism research, considers practical issues associated with application of quantitative techniques, and discusses common pitfalls and how to identify and remedy them. The result is a guide to quantitative methods in tourism that de-mystifies both simple and apparently complex techniques and makes them more accessible to tourism researchers.
Le informazioni nella sezione "Riassunto" possono far riferimento a edizioni diverse di questo titolo.
Informazioni sugli autori
Rodolfo Baggio holds a degree in Physics (MPhys) and a PhD in Tourism Management. After having worked for leading information technology firms for over 20 years he is presently at the Bocconi University, Milan, Italy, where he teaches courses in Computer Science and coordinates the Information and Communication Technologies area at the Master in Economics and Tourism. He is also Research Fellow at the Carlo F. Dondena Centre for Research on Social Dynamics. He has managed several international research projects and actively researches and publishes in the field of information technology and tourism. His current interests focus on the application of complexity theory and network analysis methods to the study of tourism destinations.
Jane Klobas is Alberto Dondena Research Fellow at the Carlo Dondena Centre for Research on Social Dynamics at Bocconi University in Milan, Italy, and Professor at the University of Western Australia Business School. She teaches quantitative research methods to undergraduate, master and doctoral degree students in Italy and Australasia, and conducts applied research using both qualitative and quantitative research methods. She is author or co-author of several books and book chapters, and has published research on the psychology and management of technology-mediated learning and knowledge sharing in many journals.
Rodolfo Baggio holds a degree in Physics (MPhys) and a PhD in Tourism Management. After having worked for leading information technology firms for over 20 years he is presently at the Bocconi University, Milan, Italy, where he teaches courses in Computer Science and coordinates the Information and Communication Technologies area at the Master in Economics and Tourism. He is also Research Fellow at the Carlo F. Dondena Centre for Research on Social Dynamics. He has managed several international research projects and actively researches and publishes in the field of information technology and tourism. His current interests focus on the application of complexity theory and network analysis methods to the study of tourism destinations.Jane Klobas is Alberto Dondena Research Fellow at the Carlo Dondena Centre for Research on Social Dynamics at Bocconi University in Milan, Italy, and Professor at the University of Western Australia Business School. She teaches quantitative research methods to undergraduate, master and doctoral degree students in Italy and Australasia, and conducts applied research using both qualitative and quantitative research methods. She is author or co-author of several books and book chapters, and has published research on the psychology and management of technology-mediated learning and knowledge sharing in many journals.
Estratto. © Ristampato con autorizzazione. Tutti i diritti riservati.
Quantitative Methods in Tourism
A Handbook
By Rodolfo Baggio, Jane KlobasMultilingual Matters
Copyright © 2011 Rodolfo Baggio and Jane Klobas
All rights reserved.
ISBN: 978-1-84541-174-9All rights reserved.
Contents
List of Examples, vii,
List of Figures, ix,
List of Tables, xv,
Contributors, xvii,
Foreword, xix,
Introduction, xxi,
Part 1: The Analysis of Data,
1 The Nature of Data in Tourism, 5,
2 Testing Hypotheses, 21,
3 Data Analysis, 42,
4 Model Building, 88,
5 Time-dependent Phenomena and Forecasting, 136,
Part 2: Numerical Methods,
6 Maximum Likelihood Estimation, 175,
7 Monte Carlo Methods, 189,
8 Agent-based Modeling and Simulations, 199,
Appendix: Software Programs, 220,
CHAPTER 1
The Nature of Data in Tourism
This chapter contains a brief review of the nature of data as used in tourism and hospitality, and discusses the main quality characteristics needed to obtain useful and reliable outcomes from data analysis. A list of the main sources of tourism data is provided.
Introduction
The protagonist in the adventures described in this book is the datum, better known in its plural form, data. The original Latin meaning, something given (and accepted as true), defines it well. It is (usually) a number, the result of some observation or measurement process, objectively representing concepts or other entities, put in a form suitable for communication, interpretation or processing by humans or automated systems. By themselves, and out of a specified context, data have no meaning at all; they are merely strings of symbols. Once organized or processed in some way, and associated with some other concepts or entities, they become useful information, assuming relevance, purpose, providing insights into phenomena, allowing judgments to be made and decisions to be taken (if interested in a discussion of these concepts, the review by Zins (2007) is a good starting point). All statistical techniques have exactly this objective.
Many disciplines, and tourism is no exception, require large quantities of data. The main challenge a researcher has today is that of managing a huge quantity, variety and complexity of data types, and of being sure to obtain useful and valid outcomes.
Data: A Taxonomy
It is possible to categorize data in several ways. One distinction is between primary and secondary data. Another classifies data by its level of measurement or measurement scale. Yet another is the medium or form from which the data are derived. We provide a brief overview of the key issues associated with data of each type here.
The distinction between primary and secondary data is made on the basis of the source of data and its specificity to the study for which it is gathered. Each type of source has strengths and weaknesses, the focus of our discussion here.
Primary data
Primary data are those collected directly from the original or 'primary' source by researchers through methods such as direct observation (both human observation and automatic collection of data such as clicks on links in Web sites or through use of other information and communications technology), questionnaire surveys (online, printed or administered by telephone or computer), structured or unstructured interviews and case studies. To be classified as primary data, the data elements collected using any one of these techniques will be unique and tailored to the specific purposes of the study conducted. The most used techniques, their strengths and limitations are well described in many books (Babbie, 2010; Creswell, 2003; Hair et al., 2005; Neuman, 2006; Phillimore & Goodson, 2004; Veal, 2006; Yin, 1994). Here, we concentrate on recent developments and issues of particular relevance to tourism research.
The main disadvantages are well known: cost and time. Collecting tailored information tends to be expensive in terms of resources needed (money and people) and it may take a long time to properly design the research and process the results. Recently, the use of the internet and the world wide web has reduced the cost and time requirements for conducting surveys. However, unless used carefully, the use of online surveys can hide problems related to the representativeness of the sample and the technical characteristics of the medium used, and individual differences among respondents can bias results. Of course, these concerns are not unique to electronic media, but can be exacerbated by the seductive ease and speed of online data collection. Indeed, many survey experts consider internet surveying (provided the sample is representative) to provide valid, reliable and relatively error-free results, among other reasons because data are captured directly from the respondent without the need for an interviewer or assistant to enter the data separately into a database for analysis (Dillman, 2007).
Regardless of the method used to capture primary data, the researcher should consider and understand well all issues associated with sampling (representativeness and sample size) and obtaining data of suitable quality. From a practical point of view, it is advisable to start any study by surveying a pilot sample and studying the responses obtained. Participants in the pilot study can be asked to identify any questions that they found difficult to understand or to answer and, using a technique known as cognitive interviewing, they can also be asked how they interpreted specific questions. The data collected from a pilot study can be used to estimate population parameters for the statistical models that will be used to draw conclusions from the final survey, information that can be used to determine the data distribution and sample size necessary or desirable for the larger-scale investigation to be conducted effectively (Dillman, 2007; Pan, 2010).
Secondary data
In many cases, collecting primary data is not within the reach of the investigator. Furthermore, it is not always necessary to have primary data to conduct a study. For example, very few researchers would start collecting primary data on the number of tourists visiting a country or on the GDP of some nations. When theoretical or practical reasons do not indicate direct collection of data, secondary data are used. Secondary data are data gathered, typically by someone else, for a purpose other than the study for which they will be used. The main sources of secondary data are government agencies (statistical bureaus, public tourism departments), international associations and institutions, private research companies and industry associations. Data from these sources are available directly from the provider organization (particularly in the case of those public institutions that have an obligation – often by law – to make public the outcomes of their activities) or from libraries and electronic databases. Often, they can be obtained from these sources over the internet. Useful data for some studies can also be found in previously published research or reports and from the databases (typically customer or visitor databases) maintained by individual organizations.
Secondary data, therefore, tend to be readily available and are often free or inexpensive to obtain. In addition, it is often possible to assemble large quantities of data and to draw the data from different sources. On the other hand, secondary data may be more difficult to use and to interpret because, typically, they were gathered by other researchers for other purposes. Extracting useful information from a source of secondary data requires an understanding of the structure of the data and the database, as well as a good understanding of the characteristics and meaning of each data element. A careful reading of the data specifications is essential in order to judge the suitability of the data for the study under way, as well as its reliability and trustworthiness.
As a final point, secondary data have often been pre-processed to give summaries, totals or averages (e.g. by country or region) and the original details cannot be easily recovered. The dangers of drawing conclusions about individuals from such pre-processed data are nicely described in Simpson's Paradox: relationships observed at the aggregate level are not necessarily the same (or even in the same direction) as relationships observed at the level from which the data were aggregated. Figure 1.1 shows the relationship between two variables, let's say hours of sunlight (on the x axis) and visitor numbers (in thousands, on the y axis). The two lines show the relationship between hours of sunlight and daily visitor arrivals in four cities in two countries over Christmas (e.g. Australia and Denmark). Both lines show a positive relationship: the more sunlight in the city at Christmas time, the more visitor arrivals they record. The dotted line shows, however, the relationship between the average number of hours of sunlight and average visitor numbers to each city. On average, the cities in one country have around 10 hours of sunlight and around 3000 visitors, while the cities in the second country have around two hours of sunlight and 7000 visitors. The dotted line shows a negative relationship between hours of sunlight and visitor arrivals. Which relationship is the right one? On which would one make plans?
Combining primary and secondary data
In many cases, the data used for a study come from different sources and a combination of primary and secondary data is quite common in tourism studies. In addition to the specific considerations of primary and secondary data, the researcher needs to keep in mind the nature of the sample and the level of aggregation of data from the different sources. Specific techniques may be needed to ensure that results are useful and to avoid errors.
Data Harmonization, Standards and Collaboration
Use of secondary data, particularly when they are obtained from multiple sources, can be greatly aided by harmonization and standards. International organizations harmonize data they draw from different countries as best they can, and record any country-specific variations from the standard data definition (such as year of data collection or age groups from which data are collected) in data specifications or metadata, but there is no universally recognized and adopted standard for many of the concepts that are important for tourism studies. Many attempts exist and international institutions have published several recommendations (see, e.g. Eurostat, 2000; Eurostat, 2002; UNSD, 2010; UNWTO, 2000), but in many cases, local variations make complete harmonization very difficult if not impossible. A good example is the classification of hospitality structures. Almost all countries (and often even regions in the same country) have developed their own schemes and the comparison between hotels in different areas of the world can become a difficult task (see, e.g. Cser & Ohuchi, 2008; Hotelstars, 2010; IHRA, 2004).
Moreover, when it comes to electronically distributed data, scarce adoption of even the existing technological standards make data collection and comparison even more difficult. A key issue is that different software applications and heterogeneous computing platforms need a way to exchange data automatically without much human intervention. This interoperability between systems (or, better, the lack of) is a problem that is most obvious in large online commercial environments, but also has significant effects on the possibility to extract and use data for research purposes. Many international efforts try to overcome this problem by attempting to set standards for the representation and exchange of electronic data in tourism. Probably the most known and diffused is the proposal made by the Open Travel Alliance (OTA: http://www.opentravel.org/), a consortium of many important companies active both in the tourism and the information technology fields. The work is done at two levels. The first one concerns the semantic aspect – standard definitions and names for the different objects (a trip, a destination, a hotel, a room, etc.) involved are set by building an ontology (i.e. an agreed classification and definition scheme) (Gruber, 1993). The second considers the technical means to store and transfer data. One proposal is the use of a service-oriented architecture (Erl, 2005) based on eXtensible Markup Language (XML) standards (see http:// www.w3.org/XML, and Harold & Means, 2004). Commercial software also exists; the Nesstar system (http://www.nesstar.com) is used by a number of national and international bodies.
An associated development is the increasing attention being paid to making the data on which research results are based openly and publicly available. Several major publishers already offer authors the possibility of making their original data available as an online supplement to a published journal article and the Scholarly Publishing and Academic Resources Coalition (SPARC, http://www.sparceurope.org), which brings together major research libraries and peak university bodies, acts as an advocate of this open data model. Nonetheless, it is rare to find original data, not only in tourism, but also in many other fields. An old joke in the life science research community is that: 'the data are mine, mine, mine' and papers have been written on the subject (Campbell et al., 2002).
One more effect of the widespread usage of computers in research concerns the increasing utilization of computational models and simulations. This increases the types of data available, but also complicates the picture, as specific information about the algorithms, the software and the different parameters used to set up a model run are important pieces of information required to repeat or evaluate results. The reproducibility of findings is central to the scientific enterprise, and one key constituent is the availability of the data and the procedures used for examination and inspection by the larger community of researchers. Thus, the increasing use of computer simulations worsens the problem, as software and algorithms that underlie these artifacts should be well verified and understood, not limited to a generic description such as the one that is normally put in a paper or a report. In some fields, particularly in the sciences, researchers are setting up environments known as collaboratories to share this critical information, but as yet there is no collaboratory for tourism data, software and routines (Sonnenwald, 2007).
We conclude this section with an example of how one journal has addressed the issue of replicability. The Journal of Applied Econometrics states: 'A special feature of the Journal is its emphasis on the replicability of results by other researchers. To achieve this aim, authors are expected to make available a complete set of the data used as well as any specialized computer programs employed through a readily accessible medium, preferably in a machine-readable form'. Hopefully, this example will be followed by many others, and modern information technologies, standards for recording and making data available and the attitude toward using them, will help by increasing the visibility and accessibility of data and algorithms.
Quantitative and categorical data
Another fundamental distinction between types of data concerns the level of measurement of the data. This distinction is well covered in statistical textbooks, but it is so critical to the selection of appropriate statistical techniques and so often ignored that we want to draw attention to it here. We will distinguish primarily between quantitative data and categorical data. Quantitative data are data measured using a numerical scale that reflects a quantity such as temperature, height, cost, age (in years), percentage satisfaction with an experience and so on. Categorical data represent qualities or characteristics that can be used to categorize a person or object; examples are gender, age group, country, approval or disapproval of a policy or plan and so on. While categorical data can be included in statistical analyses, they often require special treatment if the results are to be meaningful.
The many forms of data
One more important element when considering data is the different forms in which they are recorded and expressed. Data can be found in forms such as simple numerical quantities, high-dimensional data (i.e. multivariate data that can only be defined by recording observations on several variables), geometric or spatial records, images, graphs, texts, maps and geographical representations (Shoval, 2010). Advances in modern technologies have led us to a world in which practically every object of interest can be put in digital form. Overlaid on any one of these, there is often a temporal dimension that multiplies quantities and types to be managed by a factor equal to the number of time steps of interest; this may result in very large datasets.
Data Quality
As seen in the previous sections, the quantity and the types of data available for studying tourism matters are vast. Today, the issue of information overload is ever-present. Even if, historically, it is a common complaint born with the invention of the printing press, the modern excess of data and information poses a serious challenge. In this regard, a foremost issue is data quality. As well put by Kent (2001):
The statistics themselves are pointless unless the data on which they are performed are of good or at least acceptable quality. "Garbage in, garbage out" (GIGO) is a phrase that is commonly heard, but whose implications are seldom given the attention or credence they deserve. If the data going into the analysis are of dubious quality, then no degree of statistical sophistication can prevent the ensuing analysis being similarly suspect. (Kent, 2001: 2)
(Continues...)
Excerpted from Quantitative Methods in Tourism by Rodolfo Baggio, Jane Klobas. Copyright © 2011 Rodolfo Baggio and Jane Klobas. Excerpted by permission of Multilingual Matters.
All rights reserved. No part of this excerpt may be reproduced or reprinted without permission in writing from the publisher.
Excerpts are provided by Dial-A-Book Inc. solely for the personal use of visitors to this web site.
Le informazioni nella sezione "Su questo libro" possono far riferimento a edizioni diverse di questo titolo.
