Revealed Preference Research Articles

Combining stated and revealed choice research to simulate the neighbor effect: The case of hybrid-electric vehicles

According to intuition and theories of diffusion, consumer preferences develop along with technological change. However, most economic models designed for policy simulation unrealistically assume static preferences. To improve the behavioral realism of an energy–economy policy model, this study investigates the “neighbor effect,” where a new technology becomes more desirable as its adoption becomes more widespread in the market. We measure this effect as a change in aggregated willingness to pay under different levels of technology penetration. Focusing on hybrid-electric vehicles (HEVs), an online survey experiment collected stated preference (SP) data from 535 Canadian and 408 Californian vehicle owners under different hypothetical market conditions. Revealed preference (RP) data was collected from the same respondents by eliciting the year, make and model of recent vehicle purchases from regions with different degrees of HEV popularity: Canada with 0.17% new market share, and California with 3.0% new market share. We compare choice models estimated from RP data only with three joint SP–RP estimation techniques, each assigning a different weight to the influence of SP and RP data in coefficient estimates. Statistically, models allowing more RP influence outperform SP influenced models. However, results suggest that because the RP data in this study is afflicted by multicollinearity, techniques that allow more SP influence in the beta estimates while maintaining RP data for calibrating vehicle class constraints produce more realistic estimates of willingness to pay. Furthermore, SP influenced coefficient estimates also translate to more realistic behavioral parameters for CIMS, allowing more sensitivity to policy simulations.

Making a case for investment in the public realm

High-quality urban realm generates benefits to pedestrians in terms of improved walking experience and contributes to the socio-economic vitality of streets and neighbourhoods. However, it is very difficult to value and quantify those benefits. Historically, transport appraisal guidance has only allowed for the quantification of safety and time-saving benefits to pedestrians, which represent a small portion of benefits arising from public realm schemes. There are two main approaches to valuing the benefits to be gained from improved urban realm: the bottom-up approach of valuing benefits to individuals through stated preference (SP) and a top-to-bottom approach using revealed preference (RP). A method for quantifying user benefits using SP surveys has been developed. SP, however, only represents a partial valuation of benefits (not accounting for wider socio-economic benefits) and the values derived from SP surveys are subject to uncertainty. An alternative approach, using RP, measured the impact of public realm quality on market prices (retail rents and residential property prices). Although the results from this work showed a link between the quality of public realm and market prices, more research is needed to assess and value the benefits of public realm schemes.

COMBINING REVEALED AND STATED PREFERENCE DATA TO ESTIMATE THE NONMARKET VALUE OF ECOLOGICAL SERVICES: AN ASSESSMENT OF THE STATE OF THE SCIENCE

Abstract This paper reviews the marketing, transportation and environmental economics literature on the joint estimation of revealed preference (RP) and stated preference (SP) data. The RP and SP approaches are first described with a focus on the strengths and weaknesses of each. Recognizing these strengths and weaknesses, the potential gains from combining data are described. A classification system for combined data that emphasizes the type of data combination and the econometric models used is proposed. A methodological review of the literature is pursued based on this classification system. Examples from the environmental economics literature are highlighted. A discussion of the advantages and disadvantages of each type of jointly estimated model is then presented. Suggestions for future research, in particular opportunities for application of these models to environmental quality valuation, are presented.

Capturing Travelers' Stated Mode Choice Preferences Under Influence of Income in Yangon City, Myanmar

Focusing on the role of a new transit system (NTS) in mitigating current and future potential traffic issues in Yangon City of Myanmar, this paper attempts to analyze the mode choice behavior based on a stated preference (SP) survey. In comparison with developed countries, developing countries are characterized by rapidly changing socio-economic environments (especially, income). It is required to reflect the influence of such decision context in both survey method and modeling framework. Therefore, SP survey is first designed to incorporate the influence of future income, as well as other level-of-service attributes, whereas a revealed preference (RP) survey is also prepared. Second, a RP/SP combined mode choice model is estimated in which the parameters of travel time and cost are defined as a function of future income, respectively. A SP survey was conducted at a residential area of Yangon City in March 2003. This is the first SP survey done in Myanmar. Respondents show the highest preference of NTS among travel modes. The effectiveness of the proposed model structure was empirically confirmed. Furthermore, simulation analysis suggests that future income will bring about a potentially large increase in car usage and consequently reduction in transit systems.

Assessing systematic sources of variation in public transport elasticities: Some comparative warnings

There is an extensive and continually growing body of empirical evidence on the sensitivity of potential and actual users of public transport to fare and service levels. The sources of the evidence are disparate in terms of methods, data collection strategy, data paradigms, trip purpose, location, time period, and attribute definition. In this paper, we draw on a data set we have been compiling since 2003 that contains over 1100 elasticity items associated with prices and services of public transport, and car modes. The focus herein is on direct elasticities associated with public transport choice and demand, and the systematic sources of influence on the variations in the mean estimates for fares, in-vehicle time, and headway obtained from 319 studies. The major influences on variations in mean estimates of public transport elasticities are the time of day (peak, all day vs. off-peak), the data paradigm (especially combined SP/RP vs. revealed preference (RP)), whether an average fare or class of tickets is included, the unit of analysis (trips vs. vkm), specific trip purposes, country, and specific-mode (i.e., bus and train) in contrast to the generic class of public transport.

Consumer' Surplus, Fundamental Welfare Theorems and Revealed Preference Approach

Modern mainstream economics teach us that Marshallian consumer surplus concept can be correctly applied only in the special case of quasilinear preferences (when price of numeraire is normalized to unity), which is never observed in reality. Our paper shows the opposite: we can every time correctly apply individual and aggregate Marshallian surplus approach for the general class of differentiable preferences along subset of monotonous and piecewise monotonous parameterizations. Aggregate generalized consumer surplus - change in the sum of all consumers' incomes and net surpluses - is identically equal to the change in efficient social welfare function, if level of efficient social welfare is changing (piecewise) monotonously along adjustment path. Fundamental welfare theorems are proposed to generalization for potential application of aggregate Marshallian surplus measures and the relation between aggregated revealed preference approach, Coase' theorem, fundamental welfare theorems and representative consumer' approach is discussed.

Empirical approaches to combining revealed and stated preference data: Some recent developments with reference to urban mode choice

This paper replaces the nested logit ‘trick’ used in estimation of a modal choice model, when stated preference (SP) and revealed preference (RP) data are pooled, with an error component mixed logit model that can (i) relax the IID condition attached to subsets of alternatives in nested logit models, (ii) accommodate correlated observations, and (iii) reveal the relevant scale parameter for subsets of alternatives. Such a model can also incorporate state dependence between data types and preference heterogeneity on observed attributes. An example of choice among bus, train and car modes illustrates the difference in empirical evidence, especially elasticity outputs.

The Economics of Fish Consumption Advisories: Insights from Revealed and Stated Preference Data

Measuring how fish consumption advisories affect angler’s utility has proven difficult. Relying on stated preference (SP) data is problematic because of hypothetical bias. Revealed preference (RP) data benefits from using actual behavior; however, co-linearity often makes it difficult to model the array of advisory severity levels across different species and catch rates. The array of advisories also makes traditional joint estimation impractical. This paper describes an alternative joint estimation technique, based on an index of SP parameter, that we used for estimating the effect of fish consumption advisories on the Fox River/Green Bay.

Telecommuting and residential location decisions: combined stated and revealed preferences model

This paper reports on a combined stated preference (SP) and revealed preference (RP) model for studying the effect of telecommuting on households’ residential location decisions. Logit models were developed to estimate the parameters of the utility function. The required data for the model estimation were collected in an attitudinal survey of employees of selected private and public organizations in the Ottawa–Carleton region. The RP information included respondents’ residential, employment, and socioeconomic characteristics. To obtain the SP responses, the respondents were presented with a number of hypothetical residential choice scenarios defined on the basis of SP experimental design. The sequential maximum likelihood estimation procedure was used to obtain taste parameters of the combined multinomial logit model. The empirical case study demonstrated practical application of the method. The hybrid model is a useful tool for urban development planning. On the basis of the results, it is concluded that telecommuting is a highly significant factor in residential location decisions.Key words: telecommuting, land use, residential location, modelling, urban development, stated preference, revealed preference.

Combining RP and SP data: biases in using the nested logit ‘trick’ – contrasts with flexible mixed logit incorporating panel and scale effects

It has become popular practice that joint estimation of choice models that use stated preference (SP) and revealed preference (RP) data requires a way of adjusting for scale to ensure that parameter estimates across data sets are not confounded by differences in scale. The nested logit ‘trick’ presented by Hensher and Bradley in 1993 [Hensher, D.A., Bradley, M., 1993. Using stated response data to enrich revealed preference discrete choice models. Marketing Letters 4 (2), 139–152] continues to be widely used, especially by practitioners, to accommodate scale differences. This modelling strategy has always assumed that the observations are independent, a condition of all GEV models, which is not strictly valid within a stated preference experiment with repeated choice sets and between each SP observation and the single RP data point. This paper promotes the replacement of the NL ‘trick’ method with an error components model that can accommodate correlated observations as well as reveal the relevant scale parameter for subsets of alternatives. Such a model can also incorporate “state” or reference dependence between data types and preference heterogeneity on observed attributes. An example illustrates the difference in empirical evidence.

Modelling airport and airline choice behaviour with the use of stated preference survey data

The majority of studies of air travel choice behavior make use of revealed preference (RP) data, generally in the form of survey data collected from departing passengers. While the use of RP data has certain methodological advantages over the use of stated preference (SP) data, major issues arise because of the often low quality of the data relating to the un-chosen alternatives, in terms of explanatory variables as well as availability. As such, studies using RP survey data often fail to recover a meaningful fare coefficient, and are generally not able to offer a treatment of the effects of airline allegiance. In this paper, we make use of SP data for airport and airline choice collected in the US in 2001. The analysis retrieves significant effects relating to factors such as airfare, access time, flight time and airline and airport allegiance, illustrating the advantages of SP data in this context. Additionally, the analysis explores the use of non-linear transforms of the explanatory variables, as well as the treatment of continuous variations in choice behavior across respondents.

Factors influencing the propensity to cycle to work

This paper describes the development of a mode choice model for the journey to work with special emphasis on the propensity to cycle. The model combines Revealed Preference (RP) and Stated Preference (SP) data to form a very large and comprehensive model. RP data from the National Travel Survey was combined with a specially commissioned RP survey. A number of SP surveys were also undertaken to examine the effects of different types of en-route and trip end cycle facilities and financial measures to encourage cycling. The development of the model is described in detail. The model was used to forecast trends in urban commuting shares over time and to predict the impacts of different measures to encourage cycling. Of the en-route cycle facilities, a completely segregated cycleway was forecast to have the greatest impact, but even the unfeasible scenario of universal provision of such facilities would only result in a 55% increase in cycling and a slight reduction in car commuting. Payments for cycling to work were found to be highly effective with a £2 daily payment almost doubling the level of cycling. The most effective policy would combine improvements in en-route facilities, a daily payment to cycle to work and comprehensive trip end facilities and this would also have a significant impact on car commuting.

A Stated Preference Study for a Car Ownership Model in the Context of Developing Countries

A stated preference (SP) experiment of car ownership was conducted in Mumbai Metropolitan Region (MMR) of Maharashtra in India. A full factorial experiment was designed to considering various attributes such as travel time, travel cost, projected household income, car loan payment and servicing cost. Data on 357 individuals were collected which resulted in 3213 observations for the calibration of the work trip and recreational trip car ownership models. The car ownership alternatives considered 0, 1 and 2 cars. A multinomial logit framework was used to develop the car ownership model taking the household as a decision unit. The specification and results of the SP car ownership model are discussed. The observed and predicted values matched reasonably when the validity of the SP car ownership model was tested against revealed preference (RP) data. The car ownership models developed in this study exhibit a satisfactory goodness of fit. It is concluded that the SP modelling approach can be successfully used for modelling car ownership decisions of households in developing countries.

Disaggregate Traffic Mode Choice Model Based on Combination of Revealed and Stated Preference Data

The conventional traffic demand forecasting methods based on revealed preference (RP) data are not able to predict the modal split. Passengers' stated intentions are indispensable for modal split forecasting and evaluation of new traffic modes. This paper analyzed the biases and errors included in stated preference data, put forward the new stochastic utility functions, and proposed an unbiased disaggregate model and its approximate model based on the combination of RP and stated preference (SP) data, with analysis of the parameter estimation algorithm. The model was also used to forecast rail transit passenger volumes to the Beijing Capital International Airport and the shift ratios from current traffic modes to rail transit. Experimental results show that the model can greatly increase forecasting accuracy of the modal split ratio of current traffic modes and can accurately forecast the shift ratios from current modes to the new mode.

Analysing Demand for Suburban Trips: A Mixed RP/SP Model with Latent Variables and Interaction Effects

We analyse mode choice behaviour for suburban trips in the Grand Canary island using mixed revealed preference (RP)/stated preference (SP) information. The SP choice experiment allowed for interactions among the main policy variables: travel cost, travel time and frequency, and also to test the influence of latent variables such as comfort. It also led to discuss additional requirements on the size and sign of the estimated model parameters, to assess model quality when interactions are present. The RP survey produced data on actual trip behaviour and was used to adapt the SP choice experiment. During the specification searches we detected the presence of income effect and were able to derive willingness-to-pay measures, such as the subjective value of time, which varied among individuals. We also studied the systematic heterogeneity in individual tastes through the specification of models allowing for interactions between level-of-service and socio-economic variables. We concluded examining the sensitivity of travellers’ behaviour to various policy scenarios. In particular, it seems that contrary to political opinion, in a crowded island policies penalising the use of the private car seem to have a far greater impact in terms of bus patronage than policies implying direct improvements to the public transport service.

Welfare Economics with Intransitive Revealed Preferences: A Theory of the Endowment Effect

AbstractEconomists use the standard rational model to predict behavior after a policy change and to determine the policy's welfare implications. Recent experimental observations are casting doubt on the predictive accuracy of the standard model, but the more realistic behavioral alternatives often provide a poor basis for making normative evaluations. This paper suggests that we can still predict behavior and measure welfare within the same model. We show that optimizing agents with standard preferences will in some cases behave as if they are subject to an endowment effect. Even so, we may still be able to uncover information about their preferences.

Use of Mixed Revealed-Preference and Stated-Preference Models with Nonlinear Effects in Forecasting

Estimation of mixed revealed-preference (RP) and stated-preference (SP) data has become almost common practice. However, most attention has gone to estimation, with the correct use of these much-improved models in forecasting left in need of better understanding. In particular, their potentiality in accounting for nonlinear effect has not been fully explored, either in estimation or in prediction. The problem of using an RP-SP mixed model for accounting for nonlinear effects in the attributes in forecasting, especially when the nonlinearities have been specifically estimated only for the SP data, is addressed. By using a mixed RP-SP data set gathered especially for a modal choice context in Cagliari, Italy, several nested logit models with nonlinear systematic utility functions were estimated and used to provide empirical evidence on the effect of incorrect use of RP-SP specifications in forecasting under different policies. It was concluded that the partial data enrichment approach is well suited to treat nonlinearities and allows for consistent improvements in model estimation results. More important, nonlinearities might impose severe limitations in the applicability of these models in forecasting because of more restrictive microeconomic conditions. Failure to treat these problems correctly can lead to serious forecasting errors, even in the case of relatively mild policies.

Use of Mixed Revealed-Preference and Stated-Preference Models with Nonlinear Effects in Forecasting

Estimation of mixed revealed-preference (RP) and stated-preference (SP) data has become almost common practice. However, most attention has gone to estimation, with the correct use of these much-improved models in forecasting left in need of better understanding. In particular, their potentiality in accounting for nonlinear effect has not been fully explored, either in estimation or in prediction. The problem of using an RP-SP mixed model for accounting for nonlinear effects in the attributes in forecasting, especially when the nonlinearities have been specifically estimated only for the SP data, is addressed. By using a mixed RP-SP data set gathered especially for a modal choice context in Cagliari, Italy, several nested logit models with nonlinear systematic utility functions were estimated and used to provide empirical evidence on the effect of incorrect use of RP-SP specifications in forecasting under different policies. It was concluded that the partial data enrichment approach is well suited to trea...

On fitting mode specific constants in the presence of new options in RP/SP models

We treat the problem of fitting alternative specific constants (ASC) in models estimated with a mixture of revealed preference (RP) and stated preference (SP) data to forecast the market shares of new alternatives. This important problem can have non-trivial solutions, particularly when some of the SP alternatives are completely revamped versions of existing ones (i.e., an advanced passenger train replacing a normal railway service). As there is no explicit treatment of this problem in the literature we examined it in depth and illustrated it empirically using data especially collected to analyse mode choice in a corridor to the West of Cagliari. We propose a hopefully useful guide to this art (as no practical recipes seem to serve all purposes). Careful specification of the systematic component of utility functions in RP and SP, including the ASC, serves to illuminate the true nature of the underlying error structure in the different data sets, yielding superior forecasting models.

MODAL CHOICE MODELS ESTIMATION USING MIXED REVEALED AND STATED PREFERENCES DATA

Discrete choice demand models estimation can be performed using data on travel behavior obtained from revealed preference (RP) and stated preference (SP) surveys. RP techniques, traditionally utilized, are relative to the actual user's travel behavior in a real context. SP techniques are methodologies based on statements made by interviewees about their preferences in different choice contexts: real, hypothetical, or experimental. Therefore, a key innovation is introduced in this work: the consideration of choice alternatives not available at the time of the surveys. These techniques have been adopted for demand models calibration to predict the choices made by users and their preferences variations while the choice context changes. In particular, some multinomial logit mode choice models have been specified and calibrated. The calibrated models have been distinguished in: RP models, based on the choices made by users exclusively in the real context; SP models, based on the choices stated in the hypothetical contexts; and joint RP/SP models, using RP and SP data on the same sample. The study confirmed the utility of SP techniques for users' travel behavior analysis in a hypothetical choice context; moreover, it has confirmed that RP/SP conjoint analysis improves parameter estimation in discrete choice models.