Transport Survey Methods: Best Practice for Decision Making

This book provides an international perspective on improving information to support transportation decision making. It comprises a selection of papers plus workshop syntheses from the 9th International Conference on Transport Survey Methods in Chile in November 2011. The conference was organized into 14 workshops with both paper presentations and discussions in the workshops forming the majority of the conference activity. The papers reported primarily on research pertaining to continuous improvement in transport survey methods — the backbone of the transportation data pipeline in most countries. But some papers also addressed the new ways in which innovation — notably technological innovation — is being applied to the capture and analysis of data to produce necessary information faster, better, and less expensively. The conference program built on a rich legacy of intellectual pursuits spanning the past two decades, and it is anticipated that the conference will continue into the future. Thus, the contents of this book represent a 5–10 year view through a moving window on the international state of the practice and concerns in transport survey methods.

Purpose — In this paper we describe a total design data collection method (expanding the definition of the usual “total design” terminology used in typical household travel surveys) to emphasize the need to describe individual and group behaviors embedded within their spatial, temporal, and social contexts.

Methodology/approach — We first offer an overview of recently developed modeling and simulation applications predominantly in North America followed by a summary of the data needs in typical modeling and simulation modules for statewide and regional travel demand forecasting. We then proceed to describe an ideal data collection scheme with core and satellite survey components that can inform current and future model building. Mention is also made to the currently implemented California Household Travel Survey that brings together multiple agencies, modeling goals, and data collection component surveys.

Findings — The preparation of this paper involved reviewing emerging transportation modeling approaches and paradigms, policy questions, and behavioral issues and considerations that are important in the multimodal transportation planning context. It was found that many of the questions being asked of policy makers in the transportation domain require a deep understanding of the interactions and constraints under which individuals make activity-travel choices, the learning processes at play, and the attitudes and perceptions that shape ways in which people adjust their travel behavior in response to policy interventions. Based on the work, it was found that many of the traditional travel survey designs are not able to provide the comprehensive data needed to estimate activity-based model systems that truly capture the full range of behavioral considerations and phenomena of importance.

Originality/value of paper — This paper offers a review of the emerging transportation modeling approaches and behavioral paradigms of importance in activity-based travel demand forecasting. The paper discusses how traditional travel survey designs are inadequate to meet the data needs of emerging modeling approaches. Based on a review of all of the data needs and new data collection methods that are making it possible to observe a full range of human behaviors, the paper offers a total survey data collection design that brings together many different surveys and data collection protocols. The core household travel survey is augmented by a full slate of special purpose surveys that together yield a rich behavioral database for activity-based microsimulation modeling. The paper is a valuable reference for transportation planners and modelers interested in developing data collection enterprises that will feed the next generation of transportation models.

Purpose — To assess how cell phone technology might impact the collection of travel data in the future.

Design/methodology/approach — Two different types of cell phone enabled studies are considered. First, we examine how the text feature of phones can be used for person-to-person surveys, and second, we explore an aggregate level survey enabled by an anonymous and passive GPS trace.

Findings — This study explores the types of travel information that are likely to be inferred from text surveys and cell phone traces. It recognizes that a passive GPS trace might change the level of measurement and the inferences we make about travel behaviors.

Research limitations/implications — The study is prospective. It anticipates that over the next 10–15 years cell phone tracking technology will improve, as well as the speed and capability of algorithms for post-processing the information.

Practical implications — Cell phone enabled studies may provide a new tool and new level of measurement, as traditional survey response rates decline, and it becomes more difficult and expensive to conduct conventional travel surveys. The capacity of cell phones for travel survey work is improving, but it is not fully realizable today (2012).

Originality/value — This study provides a context to understand how the technology of the cell phone might be integrated with more traditional travel surveys to streamline data collection, and produce new types of spatial detection, measurement, and tracking.

Purpose — The Regional Household Travel Survey (RHTS) was a large-scale regional household travel survey that covered 28 counties in the New York, North New Jersey, and Connecticut regions (i.e., the New York City “megaregion”). Data collection for the survey began in October 2010 and concluded in November 2011.

The chapter discusses the multiple modes and methodologies used in the RHTS, and presents the participation rates and trip rates obtained using this multimodal approach.

Methodology/approach — This survey used a combination of web, telephone, and mail-out/mail-back methods to collect household and travel information from approximately 18,800 households. Ten percent of the sampled households participated in the survey by using wearable global positioning system (GPS) devices that collected detailed travel data which, in turn, were processed and presented back to the households in a GPS-based prompted recall interview administered by web or telephone. The GPS component was used to generate trip rate correction factors for the other 90% diary-based households.

Findings — This large regional survey was the first to use this specific combination of methods and technologies, and provides many insights into the success of targeted survey modes and methods for different population groups.

Purpose — This paper describes what the authors believe to be the first GPS-only full-scale household travel survey.

Design/methodology — The survey commenced in early 2009 with the conduct of a pilot survey to help establish various parameters and procedures for the main survey. The main survey commenced in August 2009 and was completed in August 2010. It was designed as a household travel survey to be collected steadily over a 12 month period. The target sample size was originally set at over 3500 households, although this target was reduced downwards during the course of the survey. Each household member over the age of 12 was asked to carry a GPS device with them everywhere they went for a period of 3 days. After the 3-day collection period was completed, GPS devices were retrieved from households, the data were downloaded and processing of the data commenced. The study also involved a PR survey performed on the Internet.

Findings — The paper concludes with lessons learnt from this GPS-only survey and suggestions for how future GPS-only surveys might be conducted.

Originality/value of the paper — The paper describes the first GPS-only household travel survey and concludes that it is now feasible to conduct household travel surveys by GPS.

Purpose — The paper is analysing the effect of adding a web survey to a traditional telephone-based national travel survey by asking the respondents to check in on the web and answer the questions there (Computer Assisted Web Interview, CAWI). If they are not participating by web they are as usual called by telephone (Computer Assisted Telephone Interview, CATI).

Design/methodology/approach — Multivariate regression analyses are used to analyse the difference in response rates by the two media and to analyse if respondents' answering by the two media have different travel patterns.

Findings — The analyses show that web interviews are saving money, even though a more intensive post-processing is necessary. The analyses seem to show that the CAWI is resulting in a more careful answering which results in more trips reported. A CAWI is increasing the participation of children in the survey and of highly educated. And it is offering a higher flexibility to answer after a couple of days off. The CATI is on the other hand more useful for the elderly. In addition, the CATI survey proved to be more useful for busy people and people not willing to participate in a survey at all. Young people and people with low resources who are difficult to reach by telephone are neither met on the web. Most of the differences in the response shares can be compensated by a weighting procedure. However, not all seems to be possible to compensate for. An effort to increase the number participating in the CAWI survey might increase the quality of the survey in general.

Originality/value of paper — In many countries authorities are considering how to reduce the cost of their national travel surveys. The value of the paper is to show that a combination of a CAWI and a CATI could be a good solution. Furthermore, it shows that the mixed mode could improve a CATI and therefore be the reason in itself to change methodology.

Purpose — The Department for Transport's 2011 GPS National Travel Survey (NTS) pilot study investigated whether personal GPS devices and automated data processing could be used in place of the 7-day paper diary. Using GPS technology could reduce the relatively high burden that the diary places upon respondents, reduce costs and improve data quality.

Design/methodology/approach — Data was collected from c.900 respondents. Practical changes were made to the existing methodology where necessary, including the collection of information to support data processing. Processing was undertaken using the University of Eindhoven's Trace Annotator. Results from the GPS pilot were then compared to those from the main NTS diaries for the same period.

Findings — There were no insurmountable problems using GPS devices to collect data; however, the processed GPS data did not resemble the diary outputs, making GPS unsuitable for the NTS. The GPS data produced fewer and longer trips than the diary data. The purpose of a quarter of the GPS trips was unclear, and a disproportionate share started and ended at home.

Research limitations — Further work to manually inspect trips identified via validation as unfeasible and subsequently refine the processing algorithms would have been desirable had time permitted. GPS data processing may have been hindered by missing GPS data, particularly in the case of rail travel.

Originality/value — This research used an accelerometer-equipped GPS device to better predict the method of travel. It also combined addresses that respondents reported having visited during the travel week with GIS data to code the purpose of trips without using a post-processing prompted-recall survey.

Purpose — This paper presents the process of creating a web-based travel survey tool. It aims to define advantages and disadvantages of using the web as a survey tool as well as explain the methodology involved while conducting online travel surveys and technologies that were used in the described tool.

Methodology/approach – This paper presents a web-based origin-destination travel survey tool that was developed to assess the potential of this medium to complement usual large-scale phone surveys conducted regularly in the Quebec province. The first tool (that was updated twice to answer to new needs — people-based regional survey and household-based regional survey) developed for a generator-based survey is presented and discussed. The paper namely describes the technology used as well as the particular functions, both for respondents and administrators that were developed. Particularities of the tools are introduced.

Findings — The experimentations conducted using the web-based survey tool reveal that the key components of the tool that influences the response rates and quality of responses are ease of use of the multiple elements on questionnaire such as maps and form fields and overall design quality of the user interface. While presentation of actual results after conducting surveys using the tool are not the main goal of this paper, some preliminary results such as response rates reveal that between 10% and 20% of the entire community of trip generators like universities responded to the person-based version and around 10% of the sampled households from the general population of a specific region did complete the household-based version.

Research limitations/implications — Web-based survey tools in the transportation domain are still new and are in need of a much larger research base to be able to generalize results and findings further.

Practical implications — The tool presented is using up-to-date technology and refined questionnaire design. In this optics, it tries to push the development of web-based travel surveys further in order to increase response rates and quality of responses.

Originality/value — This paper is, on one hand, one of the first to present a tool that was used for both a person-based and a household-based survey and on the other hand for trip generator communities as well as households sampled for regional surveys. It also presents in great detail the interface used in the questionnaire and the administration toolkit accompanying the web application.

Purpose — In the context of evaluating transportation and carbon emission policies, improve weekly activity and mobility scheduling survey methodology in order to enhance data quality while reducing costs and decreasing respondent burden for designing continuous self-administered surveys that are predominantly passive (or computer-assisted).

Approach — Evaluate a set of functionalities deployed in a web travel survey interface (2009) and compare with a pencil-and-paper survey (2002–2003) deployed in Quebec City that sought similar data about weekly mobility. The first used a pencil-and-paper approach complemented by interviews and telecommunications. The second used applets developed in Java, and Google Maps in order to assist geocoding of activity places and the reporting of actual trips into a relational database, while using email to recruit and support respondents.

Implications — Both of these surveys had to address specific technical and privacy challenges during deployment, making their comparison relevant for discussing some of the impacts of information technologies on spatiotemporal data quality, conviviality of survey procedure, respondents' motivation and privacy protection.

Limitations — While neither of these surveys employed movement-aware mobile devices, such as GPS loggers, some of the lessons learnt are relevant to the design issues raised by the increasing deployment of such devices in travel surveys, and by the growing need to manage complex surveys over extended observation periods.

Purpose — The main objective of this survey is to collect data for the development of six models in a freight modeling framework. The framework aims to simulate the interactions between shippers and carriers in a freight market.

Methodology/approach — A web-based survey was designed using stated preference methods and experimental auctions, to collect information about shipper and carrier behavior when facing hypothetical situations. Hypothetical situations were constructed using information collected during the survey.

Findings — The modeling results are available for one model, the carrier selection model. In this model, data were collected using stated preference (SP) methods. Nine SP designs were developed using D-designs and an approach to minimize the nonattendance problem. A multinomial probit model was used. No bias was found due to the position of alternatives on the screen, signs of the parameters are as expected, and level of service attributes are relevant in the carrier selection process.

Research limitations/implications — The final response rate was small (about 9%) which is not uncommon in surveys with freight managers. This response rate might result in nonresponse bias of the estimates, which is the subject of future research.

Practical implications — Since freight transport is the output of a freight market, the application of the freight modeling framework presented in this chapter has potential to improve forecasts of freight flows.

Originality/value of chapter — To the best of our knowledge, the survey presented in this chapter consists of an innovative data collection procedure for the development of an original freight modeling framework.

Purpose — In this chapter the three household travel survey methods PAPI (paper and pencil interview), CATI (computer-assisted telephone interview), and CAWI (computer-assisted web interview) are compared in order to show well-known and new methodological effects.

Methodology/approach — The survey concept in the Stuttgart region with the three methods (PAPI, CAPI, and CAWI) offers the possibility to analyze the differences between these methods. This approach offers various possibilities to compare the subsamples and to evaluate the effects of the different survey methods in order to ensure a high data quality.

Findings — The results show a clear tendency that retired people prefer the CATI design instead of CAWI, while younger persons prefer the CAWI design. The PAPI design seems to cover all parts of the population to the same extent and also achieves the same response levels as CATI and CAWI.

Originality/value of chapter — The three different survey methods within one survey allow on the one hand methodological analyses without distortion of results by different framework conditions. On the other hand the CATI and CAWI survey methods are relatively new in the field of multiday surveys especially in Germany.

Purpose — In order to analyse applicability, comparability and limitations of GPS technology in travel surveys, different mobility survey techniques were tested in an Austrian pilot study.

Methodology/approach — Four groups of voluntary respondents recorded their travel behaviour over a time period of three consecutive days. The groups were assigned to three different and combined methods of data collection: Paper–pencil trip diaries, passive GPS tracking, active GPS tracking and prompted recall interviews.

Findings — The resulting mobility parameters show that self-reported paper– pencil surveys yield accurate sociodemographic information on the respondents as well as trip purposes and modes of transportation, although too few trips are reported. Passive GPS-based methods minimize the strain for respondents. Methods that combine GPS-based data collection and questionnaire provide the most reliable mobility data at the moment.

Research limitations/implications — Due to funding restrictions the sample sizes had to be relatively small (235 participants). Further development in research methodology will increase the effectiveness of automated data analysis, for example more accurate detection of activities and transport modes. The usefulness of GPS-based data collection in a large-scale surveys is planned to be tested in the next Austrian national travel survey.

Originality/value of paper — The pilot study allows a detailed comparison of traditional and GPS-based travel survey methods for the first time, due to data collection combined with prompted recalls.

Purpose — The purpose of the chapter is to make retrospective data from biographic surveys comparable with traditional cross-section travel surveys, by correcting some biases attached to the biographic collection method. This is applied to a biographic survey passed in France within the 2007–2008 national travel survey.

Methodology/approach — The methodology implemented deals with three specific biases: the general survey sampling and response rate, the survival bias, due to differential surviving rates according to generations, and the geographical bias, as biog‘raphies were not passed in all regions. All biases were corrected by computing specific weightings.

Findings — One main finding is that with these three corrections, biographic data can yield modal shares for commuting trips to work and for commuting trips to education that are similar to those derived from the historical cross-section surveys about regular trips.

Research limitations/implications — Though biographic collection suffers from the memory effect, this effect remains low and does not disturb the modal shares derived from biographies.

The most challenging issue is that of missing generations that contributed to past mobility. But they can be replaced by modeling with an age-period model.

Practical implications — The chapter provides methodology to correct biographic data to reconstitute historical behavior.

Social implications — Exploring the memory of living people is essential to save data about the past, that otherwise could be lost, although they may be useful to understand present behavior and future likely trends.

Originality/value of chapter — Investigating biographic surveys is a new topic in the field of transport survey methods.

Purpose — This study proposes an optimal survey design method for multi-day and multi-period panels that maximizes the statistical power of the parameter of interest under the conditions that non-linear changes in response to a policy intervention over time can be expected.

Design/methodology/approach — The proposed method addresses balances among sample size, survey duration for each wave and frequency of observation. Higher-order polynomial changes in the parameter are also addressed, allowing us to calculate optimal sampling designs for non-linear changes in response to a given policy intervention.

Findings — One of the most important findings is that variation structure in the behaviour of interest strongly influences how surveys are designed to maximize statistical power, while the type of policy to be evaluated does not influence it so much. Empirical results done by using German Mobility Panel data indicate that not only are more data collection waves needed, but longer multi-day periods of behavioural observations per wave are needed as well, with the increase in the non-linearity of the changes in response to a policy intervention.

Originality/value — This study extends previous studies on sampling designs for travel diary survey by dealing with statistical relations between sample size, survey duration for each wave, and frequency of observation, and provides the numerical and empirical results to show how the proposed method works.

Purpose — The paper aims at an improvement of the understanding, how mobility is reported in longitudinal surveys and to develop ideas how to assess the completeness of the reported mobility.

Methodology/approach — Analyses of data quality and completeness are performed on the multiday and multiperiod data of the German Mobility Panel. Distinctions are made between differing reporting behaviours of individuals who either reported three times, two times or only once.

Findings — It can be shown that the reporting behaviours are different depending on the number of repetitions. The results illustrate that on the one hand individuals who repeat the survey in a consecutive wave tend to report with greater motivation, endurance and accuracy. On the other hand, participants who have not reported completely and accurately are more likely to drop out. These effects positively influence the quality and completeness and therefore the reliability of recorded mobility figures in multiperiod mobility surveys.

Practical implications — The analytical possibilities of combined multiday and multiperiod data in terms of the assessment of data quality will be demonstrated. Hints to identify such types of survey artefacts are presented.

Purpose — In the context of the study of the role of social networks in travel behavior, this chapter adds to that body of knowledge by presenting a new data collection effort, which collects a wide array of information about the social, urban, and temporal context where social activity-travel behavior occurs.

Methodology/approach — The study was developed in Concepción, Chile, involving 240 respondents from four different urban contexts and their personal networks. The analysis concentrates on the challenges and opportunities of different techniques to build personal networks as a way of studying the social dimension of travel behavior. Although most of the current methods to study personal networks rely on emotional closeness, this approach may not be sufficient, since these “elicited” people may not include daily contacts that could be relevant to study social activities. Tackling this issue, the data instrument also collects those daily “revealed” people, on a two-day time use diary and a social activities listing. With this information, the chapter presents a comparative analysis between these “elicited” and “revealed” personal networks.

Findings — Overall, the results illustrate the dependence of the name generator technique on what is observed in terms of social activity-travel behavior, specifically on aspects such as personal network size, average distance, and frequencies of interaction. In addition, the comparison between the different methods to construct the personal networks, illustrates how name generators provide the opportunity to further understand transport related questions, such as the role of income and access to amenities on spatial and temporal patterns of social interactions, and their effect on social capital.

Purpose — This paper explores the potential of ‘action research’ as transport survey method, with particular emphasis on critically assessing its utility in the resolution of major transport policy challenges, such as the mitigation of climate change and environmental impacts, transport-related social exclusion and intergenerational equity issues. Although not particularly novel within the social sciences, it is an approach that has been largely overlooked within the field of transport studies to date.

Methodology/approach — The paper presents practical examples of where action research has been used to elicit information about people's travel experiences and behaviours and discusses how it achieves different outcomes from other qualitative transport survey methods. It identifies appropriate contexts for action research and explores the skills and techniques to overcome some of the main criticisms of the method. It then evaluates some of the critical challenges of applying an action research approach and identifies potential ways for overcoming these. Finally, it discusses the key challenges for analysis, presentation and dissemination of their action research ‘data’ and potential ways of overcoming these.

Findings — Action research has a long history within the social sciences, dating back to practical problems in wartime situations in Europe and the United States. It can be applied at either the level of individuals, small groups and/or ‘communities’ and organisations, with the expressed aim of bringing together research enquiry and future policy or planned actions (ibid). It provides a useful additional survey technique for policy-makers wishing to understand the detailed process of travel behaviours and barrier to travel at the individual level.

Originality/value of the paper — The action research method is specifically useful for supporting and actively encouraging behaviour change as an integral part of the research process. It has only recently emerged within the literature as a transport survey method. It can be a particularly useful method for developing more collaborative data collection methods research participants enquires and thus enable us to identify their underlying motivations, intentions, perceptions and negotiations, as well as the micro-level impacts of smaller scale transport initiatives.

Purpose — The principal hypothesis of this program of research is that people's choices of which resources to own are a function of expected travel needs.

Methodology/approach — This chapter reports recent research using a stated-choice survey design that is innovative in two respects. First, respondents are asked to consider two types of choice having different time horizons but which are thought to be linked in a strategic-tactical structure. The two types of choices are (a) purchasing ‘mobility resources’, which include commitments such as car ownership and subscription to carsharing services and (b) choosing a mode of transport for a particular instance of travel. The second methodological innovation is that respondents indicate their choices in the context of giving advice to a demographically similar ‘avatar’.

The development of a technique for ‘empirically constrained’ efficient design is discussed, as is its application to this survey. This objective is to provide survey designs with a high degree of statistical efficiency whilst maintaining plausibility in the combination of attribute levels. Field data from an empirical application (n = 72) was collected and analysed.

Findings — The proposed method for efficient design proved successful. The main substantive findings from the empirical application are presented, along with detailed results relating to how different demographic classes of respondents engaged with the instrument. For instance, living with one's partner and living with no children at home were associated with high scores on a scale of similarity between the experimental choice context and one's real-world mobility choices.

Research limitations/implications — The proposed techniques appear promising, though the empirical results must be viewed as indicative only due to the size and coverage of the field data sample.

Purpose – Departure time choice not only depends on the desire to carry out activities at certain times and places; it is a complex decision making process influenced by travel conditions, congestion levels, activity schedules, and external trip factors. To estimate departure time choice models capturing the factors influencing it in appropriate form, a complex data collection procedure allowing to obtain detailed input data from different sources and at different time periods is required.

The main aim of this chapter is to describe and discuss the survey methodology we used in a time-of-day choice project, involving the collection of revealed preference (RP) and stated preference (SP) data to estimate hybrid discrete departure time choice models incorporating latent variables. Preliminary model results are also presented as an example.

Methodology/approach – Data was obtained from 405 workers at different private and public institutions located in the centre of Santiago, Chile. The survey process had three different stages and used various collection methods (e-mail, web-page, and personal interviews at the workplace) in order to satisfy efficiency, reliability and cost criteria.

The RP component survey design was based on the last origin-destination survey implemented in Santiago (i.e. a travel diary filled under an activity recall framework). Relevant level-of-service measures at different time periods were obtained from GPS data measured from instrumented vehicles in the public and private transport networks. A SP-off-RP optimal design considering dependence among attribute levels was also developed. Finally, several 1–7 Likert scale questions were included to incorporate the latent variables.

Findings – The survey methodology described in this chapter represents a successful experience in terms of collecting high quality data, from different sources, with the aim of estimating appropriate time-of-day choice models. The data collection process was carried out in different stages, by means of web pages, email, and personal interviews. The data was further enriched with level-of-service attributes measured at different times of the day with unusual precision. Preliminary results reported in this chapter show that data obtained through this methodology are appropriate to model time-of-day choices.

Originality/value of chapter – The novelty of the survey methodology described in this chapter is the collection of data of a different nature for time-of-day choice modelling through the integration of different collection techniques.

Acquisition of very precise information about preferred departure/arrival times, level of service at different times of the day, detailed information about flexibility in schedules, employment information and attitudes towards departure times, should allow practitioners to estimate hybrid time-of-day choice models incorporating latent variables.

Purpose — A new method of collecting hurricane evacuation data using time-dependent stated choice is developed and evaluated in this study.

Methodology/approach — Hypothetical storms are presented in a video in a sequence of scenarios showing prevailing conditions at discrete points in time as each storm approaches land. Respondents are exposed to nine hypothetical storms representing a range of hurricane characteristics. One of the hypothetical storms is secretly the same as an actual storm the respondents experienced in the past and for which they are required to report their behaviour in a revealed preference survey.

Findings — Stated and actual behaviour was compared and general agreement was found between what people say they would do and what they did. The revealed preference (RP) data was supplemented with time-dependent data from official sources and hurricane evacuation demand models estimated on this enhanced RP data, as well as on a combination of the enhanced RP and time-dependent stated choice (SC) data. When the models were applied to a different data set than the ones on which the models were calibrated, the combined time-dependent RP/SC model performed slightly better than the enhanced RP model. Detailed accounting revealed that time-dependent SC data is 25 percent more expensive to collect than enhanced RP data, although some of this cost may be due to the first-time collection of this type of data.

Purpose — The research was designed to explore people's willingness/ability to understand complex road user charges. However, the results raise issues about respondent engagement and ecological validity and so have important implications for questionnaire practice.

Methodology — Computer-based experiments administered in the United Kingdom and Germany gathered respondents' estimates of road user charges along with their response latencies, personal characteristics, acceptance of road charging, assessments of task complexity and attitudes to analytical tasks.

Findings — The results demonstrate questionnaire learning effects and show the effect of personal characteristics on the accuracy and speed of questionnaire completion. The tendency of males, younger people and students to complete the task more quickly is interesting as is the fact that fewer and smaller errors were made by participants who claimed to gain satisfaction from completing a task which has involved mental effort. Engagement was seen to vary with personal characteristics, attitudes to decision making, task complexity and acceptance of the policy being tested. A key finding is that disengagement was more evident among participants who were broadly supportive of road charging than among those who were not.

Implications — The findings have important implications for the design of data collection exercises and for the interpretation of resulting data. It is concluded that repeated choice experiments are an inappropriate source of data on responses to unfamiliar circumstances. The collection of data on response latencies and the inclusion of questions on respondents' attitudes to task completion is a strongly recommended addition to standard questionnaire practice. The extent to which disengagement in an experimental context is, or is not, indicative of real-world behaviour is an important and urgent subject for further research.

Purpose — The paper reports on a research project exploring new approaches for analysing travel demand induced by changes in generalised costs of travel and activity participation. The description of the survey approach, which to our knowledge is novel in its application, reports descriptive analyses of the respondents' reactions to the changes implied in the household interviews.

Methodology — A sample of respondents were administered a 5 day travel diary, from which 1 day was selected for further analysis. Travel times for trips conducted that day were changed using predefined heuristics based on the household characteristics to attain significant changes in the generalised costs of the reported trips. Respondents were then presented with these hypothetical scenarios in face-to-face interviews. All household members were asked to state how the implied changes would have affected their activity scheduling on the specified day, i.e. to adapt their reported schedule to the new conditions.

Findings — The postulated induced travel effect could be observed, in that the modifications to the generalised costs of travel affect the respondents' travel patterns in general, and the number and durations of conducted out-of-home activities in particular. However, the predominant reaction to changing travel times is the adaptation of departure time, which does not directly interfere with trip generation. Indicators of the effects have been shown, and are quite weak as far as activity generation effects are concerned. The activities most likely to be re-planned are leisure activities and sojourns at the home location, as is consistent with expectations.

Purpose — New methods of measuring user satisfaction in transport services have been proposed and applied in the literature. In this paper, we compare three alternative measures for estimating user satisfaction: the numerical rating, the ordinal rating and the choice.

Approach — We analysed these measures considering their differences and limitations and the models that use these measures as dependent variables. We developed and applied a methodology to build these models. It comprises a preliminary qualitative analysis and a quantitative survey to identify the most relevant attributes of the satisfaction function, and a stated preference survey to obtain information of the alternative satisfaction measures for modelling purpose.

Findings — The ordinal rating may be a better user response to estimate satisfaction than score and choice based on its characteristics. The results obtained in the application reinforced this approach.

Research limitations — It is assumed that choice, score and ordinal valuation depend upon a latent stochastic satisfaction function of the same attributes. Further research is needed to analyse this assumption and how these responses vary according to the context for decision and exogenous factors, including the response scale of ratings.

Practical implications — Gathering alternative satisfaction responses simultaneously from users allowed for the consistency analysis and filtering of data, which greatly benefited the model estimation process.

Originality/value — The paper provides a methodology to estimate user satisfaction models in transit services, which can be applied in other transport services. The conceptual analysis and the application suggest that ordinal ratings are key user responses to uncover the underlying satisfaction function.

Purpose — Study the causal effect of psychological factors on mode choice, using an instrument which gathered attitudinal, affective and habitual behaviour factors, with an application to a Canadian and Chilean sample.

Approach — Ad hoc questionnaire used to collect information related to psychological factors, studying the role of these factors upon mode choice using structural equation modelling, combining a measurement model and the latent variables.

Findings — Emotional (affective) factors have a strong influence on mode choice, as well as attitudinal and habitual factors. Car users have a strong positive emotion to the transport mode they use when compared with public transport users and transit utilization.

Research limitations — The inclusion of social factors, such as norm, role and self-concept, is desirable for a better understanding of people's behaviour regarding transport mode usage. The structural equation modelling was used to analyse the causal effects among factors, but it is not intended to model mode choice. An advanced approach would be to estimate a hybrid discrete choice model.

Practical implications — Realizing the real importance of personal psychological factors on mode choice is a key issue when intending to implement mobility and travel demand management strategies. The success of these strategies strongly relies on people's change of behaviour, which does not depend only on instrumental and socio-demographic factors, such as cost, time and income, but also on these very inner personal aspects.

Originality/value — Capture psychological factors through a comprehensive survey, which rests on a psychological framework and considers simultaneously attitudinal, affective and habitual personal factors, as well as instrumental and socio-demographic information. Make a comparison among cities belonging to different countries regarding the role of these factors, cities with a different cultural and social background.

Purpose — Fare validation data from transit smart card automatic fare collection (AFC) systems have properties that align with the direction of large-scale mobility surveys and the evermore demanding data needs of the transit industry. In addition to applications in transit planning and service monitoring, travel patterns and behaviour can effectively be studied by exploiting the continuous stream of observations from the same card. The paper proposes a methodology to enrich fare validation data in order to generate information that is hard to obtain with traditional travel surveys.

Methodology/approach — The methodology aims to synthesize individual-level attributes by summarizing multi-day validation records from each card. These new dimensions are then transposed to various levels of aggregation and studied simultaneously in multivariate analysis. The methodology can also be applied to synthesize other multi-day attributes and is transferable to other modes and other travel behaviour studies.

Findings — Results show that validation data can effectively be used to measure the distribution of travel patterns in time and space as well as the variation of those phenomena over time. The paper provides several examples based on millions of validation records from the metro sub-network of Montréal, along with interpretations and some practical implications.

Research limitations/implications — Limitations and bias regarding the data and the methodology as well as the strategies to handle them are discussed within the context of passive travel survey and travel behaviour studies.

Practical implications — Practitioners in transit planning, operations, marketing and modelling can benefit from studying the increasingly accessible and massive smart card datasets through a deeper understanding of multi-day travel patterns and behaviour of transit users.

Originality/value — This paper outlines a data modelling approach and simple-to-implement methodology which exploit the multi-day property of fare validation data from a smart card AFC. The concept of multi-day attributes is introduced. The analyses show that the approach is effective for extracting information on travel behaviour and its variation which would otherwise be hard to obtain through traditional travel surveys, opening up another dimension of this data source for practitioners and transport modellers alike.

Purpose — The introduction of new technology to public transport systems has provided an excellent opportunity for passive data collection. In this paper, we explore the possibility of automatically generating level of service indicators that could be used for operation planning and monitoring of Transantiago, the public transport system of Santiago, Chile.

Design/methodology/approach — After basic processing of the raw automatic vehicle location (AVL) and automatic fare collection (AFC) data, we were able to generate bus speed indicators, travel time measurements and waiting time estimates using data from 1week. The results were compared with manual measures when available.

Findings — The advantage is that these measurements and estimates are reliable because they are obtained from large samples and at nearly no cost. Moreover, they can be applied to any set of data with a selected periodicity.

Research limitations — The scope of this research is limited to what can be observed with AVL and AFC data. Additional information is required to incorporate other dimensions, such as personal characteristics and/or more detail in the origin/destination (OD) of the trips.

Practical implications — Nevertheless, these results are valuable for the planning and operation management of public transport systems because they provide large amounts of information that is difficult and expensive to obtain from direct measurements.

Originality/value — This paper proposes tools to obtain valuable information at a low cost. These tools can be implemented in many cities that have certain technological devices incorporated into their public transport systems.

Purpose — Automated fare collection systems implemented in public transportation systems in the last decade have provided a massive, continuous and low-cost source of reliable travel information. A direct and useful application of these data is the estimation of highly representative, although not bias-free, origin-destination (OD) matrices.

Methodology/approach — We discuss several issues with current OD matrix estimation methodologies, such as fare evasion and group travel, and their derived biases, specifically focusing on the Santiago (Chile) case. We also propose and apply two methods of validation: endogenous and exogenous validation. We elaborate on some methodological improvements that could be implemented to upgrade the activity estimation mechanics.

Findings — Several sources of bias in the estimation of OD matrix estimation from passive data are pointed and some solutions proposed. We apply improvements to existing methodologies and increase the success rate of trip estimations.

Practical implications — The reliable estimation of public transport OD matrices from passive data results in a valuable planning tool for both transit authorities and operators, much more representative and with less errors and biases that conventional data collecting techniques.

Originality/value of paper — This paper is one of the first works to deal with the subject.

Purpose — Describe the system set-up and processing requirements for a long-duration longitudinal Global Positioning System (GPS)/prompted-recall (PR) survey conducted in Sydney, Australia and assess reaction and cognition of participants.

Design/methodology/approach — The survey uses data collected using an in-car GPS device within a PR interface accessed over the Internet by participants. Technical requirements, interface design and survey administration of the survey are discussed. This is followed by an assessment of participant burden and cognition by analysing user activity on the PR and comparing participant responses to information inferred from the GPS data.

Findings — New technologies have allowed for increasingly sophisticated data collection efforts but they require substantial resources to translate this into a usable form. This study shows these technologies can be used to conduct long-duration travel studies in a way that is appealing and engaging to participants. However, it was found that responses to the PR are sometimes inconsistent and caution should be drawn in taking PR responses as the ‘ground truth’.

Research limitations/implications — The relatively low participant burden of this study shows long-duration studies are feasible if care is taken to limit the work required by participants. The inconsistency of the responses to the PR suggest future surveys may need to employ mechanisms that are better able to aid participants in accurately completing the survey.

Originality/value — Details the requirements of running a long-duration GPS/PR survey and assesses participant burden and cognition of the survey which are often not reported.

Purpose — In this chapter, we will review several alternative methods of collecting data from mobile phones for human mobility analysis. We propose considering cellular network location data as a useful complementary source for human mobility research and provide case studies to illustrate the advantages and disadvantages of each method.

Methodology/approach — We briefly describe cellular phone network architecture and the location data it can provide, and discuss two types of data collection: active and passive localization. Active localization is something like a personal travel diary. It provides a tool for recording positioning data on a survey sample over a long period of time. Passive localization, on the other hand, is based on phone network data that are automatically recorded for technical or billing purposes. It offers the advantage of access to very large user populations for mobility flow analysis of a broad area.

Findings — We review several alternative methods of collecting data from mobile phone for human mobility analysis to show that cellular network data, although limited in terms of location precision and recording frequency, offer two major advantages for studying human mobility. First, very large user samples – covering broad geographical areas – can be followed over a long period of time. Second, this type of data allows researchers to choose a specific data collection methodology (active or passive), depending on the objectives of their study. The big mobile phone localization datasets have provided a new impulse for the interdisciplinary research in human mobility.

Originality/value of chapter — We propose considering cellular network location data as a useful complementary source for transportation research and provide case studies to illustrate the advantages and disadvantages of each proposed method. Mobile phones have become a kind of “personal sensor” offering an ever-increasing amount of location data on mobile phone users over long time periods. These data can thus provide a framework for a comprehensive and longitudinal study of temporal dynamics, and can be used to capture ephemeral events and fluctuations in day-to-day mobility behavior offering powerful tools to transportation research, urban planning, or even real-time city monitoring.