Quantitative Tools: Discrete Choice Modelling

The Choice Modelling and Valuation Group has made major innovations and extensions to best practice in the area of discrete choice modelling, as a means by which to understand and predict choice behaviour.

Where appropriate we develop models using information from choices that people are observed to make, referred to as revealed preference (RP) information. In cases where there are limitations in the information provided by observed choices, for example when predicting demand for a new product or service, we collect stated preference choice information (SP data).

A number of procedures for eliciting stated responses exist, but current practice focuses on the use of discrete choice experiments (DCE), which involve the presentation of hypothetical choice situations to respondents in surveys. In SP DCE each alternative is described by its relevant attributes, for example, the quality of the service, the cost of the service, future characteristics, etc. Each of the attributes in the experiment is also described by a number of levels, e.g. low cost versus high cost. The attribute levels are combined using principles of experimental design to define different packages of goods or services which individuals then compare in surveys.

The outputs from discrete choice models can be used to improve understanding of the drivers of people’s choices, including:

  • estimates of the relative importance of different attributes for a specific product or service, for different population groups
  • estimates of the trade-offs or marginal rates of substitution that people are willing to make between attributes, providing indirect measurements of willingness to pay.

The outputs from discrete choice models can also be used to develop predictive models to gain insight into how people's choices may change under differing circumstances. Using these models is particularly useful for policymakers to demonstrate the likely impacts of a policy. The models can provide estimates of changes in demand for services, as well as insight into how a policy may impact different groups within society. The models can also quantify how individual attributes influence demand, thereby providing estimates of elasticities, as well as providing estimates of consumer surplus, i.e. monetary valuation of the benefits obtained from different services.

An important benefit of the rigorous statistical procedures we employ is that information can be given on the accuracy of all the outputs of the model, as well as indicating whether specific aspects of the choice are truly significant in influencing behaviour.

RAND Europe was one of the first companies to employ SP DCE in the transport sector and continues to conduct research to improve SP methods. RAND Europe pioneered procedures to combine RP and SP data to exploit the strengths of each of the data types to best advantage. We also offer expertise in RP and SP survey design, based on insights gathered from our extensive practice in RP and SP modelling.

Current Projects

  • Assessing the Public Perception of Security and Privacy in Europe

    Security technologies and related measures are implemented to mitigate likely risks from terrorist attacks and other threats, but these technologies and measures may compete with privacy and civil liberties. RAND Europe is participating in PACT, a 3-year EU-funded research project to assess existing knowledge about the relation between security and privacy; collect empirical evidence through a pan-European survey; and analyze the main factors that affect how the public perceives the security and privacy implications of security technology.

  • Examining the Feasibility of Time-of-Day Tolls to Reduce Congestion

    To reduce traffic along a heavily congested Texas toll road, researchers are using stated preference surveys and discrete choice models to understand how motorists will respond to alternative time-of-day pricing policies.

  • Modelling the Demand for Postal Products

    The UK postal market has changed significantly over recent years with the introduction of greater competition and the development of new postal products. Royal Mail has commissioned RAND Europe to undertake choice modelling research to gain a more detailed understanding of how business customers choose different products under current, and a range of possible future, market conditions.

  • Estimating the Value of Mobile Telephony in Mobile Network 'Not-Spots'

    Around 80,000 premises in the UK are located in areas without mobile phone coverage – referred to as “not-spots”. Researchers are estimating the social, economic and environmental impacts associated with eliminating mobile not-spot areas in England.

  • "Living with Breathlessness" Seeks Better End-of-Life Care for COPD Patients

    Chronic obstructive pulmonary disease (COPD) accounts for one death every 20 minutes in England and Wales. RAND Europe and the University of Cambridge are conducting a study on "Living with Breathlessness" to improve the end-of-life care strategy for patients with advanced COPD: one which is based on a recognition of the slow relentless progression of non-malignant disease, its effect on patients and care-givers, and their stated care preferences.

  • Understanding Physicians' Decision-Making Process Concerning Hepatitis-C Treatment

    When treating patients for Hepatitis-C, physicians may be influenced by many factors: their prior experience, the health and social care systems more broadly, or clinical, social and behavioural, or demographic factors. To better understand this decision-making process, GlaxoSmithKline commissioned RAND Europe to investigate the comparative influence and importance of specific factors and combinations of factors and their trade-offs.

Completed Research

  • Book Offers Expert Overview of Choice Modelling

    08 Sep 2014

    Choice modelling is a key tool for the understanding of behaviour and is used to support decision-making in fields such as transportation, health economics, environmental analysis and marketing. The Handbook of Choice Modelling — edited by Andrew Daly and composed of contributions from Daly, Peter Burge, and other senior figures in the field — provides an authoritative and in-depth overview of the essential topics related to choice modelling.

  • Factors Influencing Students' Choice of University in England

    12 Jun 2014

    RAND Europe used choice experiments to provide fresh empirical evidence on the relative influence of tuition fee levels and other factors on the decisions of those choosing between universities. Employment prospects, living expenses, university location, course quality and tuition fees were all important.

  • Measuring the Public Acceptability of Population-Level Interventions to Reduce Alcohol Consumption

    28 May 2014

    Public acceptability influences policy action, but the most acceptable policies are not always the most effective. The findings of a discrete-choice experiment suggest that public acceptability of alcohol interventions is dependent on both the nature of the policy and its expected effectiveness. Policy-makers struggling to mobilise support for hitherto unpopular but promising policies should consider giving greater prominence to their expected outcomes.

  • Consumers' Responsiveness to Alcohol Multi-buy Sales Promotions

    22 Jul 2013

    Multi-buy promotions have a large impact on which alcohol products consumers purchase, according to stated-preference research by RAND Europe for Her Majesty's Revenue and Customs. The overall impact on all alcohol purchasing is somewhat smaller, though still substantial: Moderate drinkers are more likely to be swayed by these promotions, but because hazardous and harmful drinkers purchase much higher volumes of alcohol, the absolute impact on these groups is higher.

  • Measuring Consumer Preferences for Postal Services

    05 Apr 2013

    When it comes to European postal services, it is clear that different market segments have different needs. RAND Europe, in conjunction with Accent and Swiss Economics, undertook a study for the European Commission to help identify consumer needs in relation to postal services. Among the conclusions: big business valued letter services more than did small and medium enterprises or the public, whereas all consumers valued parcel services as well as high levels of reliability and low levels of loss. The research was conducted using stated preference experiments in three countries.

  • What Types of Interventions Change Energy Using Behaviours?

    12 Dec 2012

    The UK Department for Energy and Climate Change (DECC) was interested in understanding the effectiveness of interventions designed to change energy use behaviour in the home. They commissioned RAND Europe to assess the state of knowledge about “what works”, by systematically reviewing previous trials and initiatives, drawing on evidence from the UK and abroad. This review has informed DECC’s November 2012 Energy Efficiency Strategy, which sets out their policy direction for decades to come.

  • Do Attitudes Affect Choices, or Vice Versa?

    19 Aug 2011

    Growing interest in the use of models that recognise the role of individuals' attitudes and perceptions in choice behaviour has influenced a team of RAND Europe researchers to examine the latent nature of attitudes. In an article in Transportation they present an application of jointly estimated attitudinal and choice models to a real-world transport study, looking at the role of latent attitudes in a rail travel context. The result of their work is an ordered logit structure that explains how the choices people make may be strongly influenced by their attitudes, but that the choices also say something about those attitudes.

  • Does Patient Choice Influence Healthcare Services Quality?

    07 Mar 2011

    The policy of offering patients a choice in where they receive hospital treatment was intended to create competition among providers and to improve quality of care, but it has not succeeded. Patients say they value aspects of quality when choosing a hospital, but few actually consult published performance information and instead opt to be treated by their local provider. Moreover, the 'threat' of patient choice has led few hospitals to try to improve their reputation.

  • How Much Are People Willing to Pay to Reduce Carbon Emissions?

    28 Feb 2011

    To combat climate change, the British government has thus far valued the cost of carbon emissions based on how much people should pay, rather than how much they are willing to pay, or the value they place on carbon emissions reduction. An analysis of a series of RAND Europe studies suggests there is an opportunity for a large consumer surplus — a social benefit — by introducing a carbon tax to pay for the damages caused by carbon emissions.

  • How Do the Public Value Different Outcomes of Social Care?

    10 Jun 2010

    Social care is an increasing important public service, but little is known about its impact and how effective or efficient different care interventions are. To help remedy this situation, RAND Europe has undertaken research for the Office of National Statistics and the Personal Social Services Research Unit that quantifies the value placed on different aspects of social care related quality of life. This research forms part of the new Adult Social Care Outcomes Toolkit (ASCOT), which provides a tool for commissioners, service providers and regulators to quantify the outcomes of care interventions and help prioritise expenditure in areas which offer the greatest return to service users.

  • Reviewing Methods for Understanding Customer Responses to Market Changes

    29 Apr 2010

    Competition authorities and regulators often need to understand how customers will respond to price changes, whether they will switch providers if there are changes in the market, and the value that they put on alternatives and their attributes. The UK Competition Commission commissioned RAND Europe to review the methodological options available for carrying out stated preference studies to answer such questions and to advise on the design of and market research methods to conduct such studies.

  • Security, At What Cost? Quantifying People's Trade-Offs Across Liberty, Privacy and Security

    11 Jan 2010

    To understand the privacy, liberty, and security trade-offs individuals are willing to make, and so policy makers can be better informed about citizens' true preferences in this domain, RAND Europe undertook an innovative stated-preference discrete-choice modelling study. The research included three real-life case studies where these factors come into play: applying for a passport, traveling on the national rail network, and attending a major public event such as the opening ceremony of the Olympics.

  • Quantifying Customers' Priorities for Electricity Distribution Services

    08 Sep 2008

    Britain's gas and electricity regulator, Ofgem, undertakes price reviews every five years to set a price control regime for regional operators. For the last review, Ofgem commissioned a national research programme to identify and quantify customers' priorities for electricity distribution improvements. RAND Europe's effort focused on the design and analysis of stated preference choice experiments to measure customers' willingness to pay or to be compensated for electricity service changes.