nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2017‒04‒02
seven papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. Stated Preferences for Space Heating Investment By Elena Stolyarova; Hélène Le Cadre, MINES ParisTech, PSL Research University, Centre for Applied Mathematics; Dominique Osso, EDF R&D, ENERgie dans les BAtiments et les Territoires; Benoit Allibe
  2. Cultural identity and willingness to protect and preserve art By M. Meleddu; C. Detotto; M. Vannini
  3. Is Forest Landscape Restoration Socially Desirable? A Discrete Choice Experiment Applied to the Scandinavian Transboundary Fulufjället National Park Area By Sviataslau Valasiuk; Mikołaj Czajkowski; Marek Giergiczny; Tomasz Żylicz; Knut Veisten; Askill Harkjerr Halse; Iratxe Landa Mata; Marine Elbakidze; Per Angelstam
  4. Stated Preferences for Conservation Policies under Uncertainty: Insights on Individuals’ Risk Attitudes in the Environmental Domain By Michela Faccioli; Laure Kuhfuss; Mikolaj Czajkowski
  5. The Allure of the Illegal: Choice Modelling of Rhino Horn Demand in Vietnam By Nick Hanley; Oleg Sheremet; Martina Bozzola; Douglas C. MacMillan
  6. Granger causality in dynamic binary short panel data models By Bartolucci, Francesco; Pigini, Claudia
  7. Public transport: one mode or several? By Lorenzo Varela , Juan Manuel; Börjesson, Maria; Daly, Andrew

  1. By: Elena Stolyarova; Hélène Le Cadre, MINES ParisTech, PSL Research University, Centre for Applied Mathematics; Dominique Osso, EDF R&D, ENERgie dans les BAtiments et les Territoires; Benoit Allibe
    Abstract: this paper, we use a discrete choice experiment on space heating for both detached houses and apartments in France. In our choice experiment, we asked 1,820 respondents, both owners and tenants, to imagine that their current space heating system had broken down and that they had to choose a new one to replace it. A multinomial logit model was used to analyze the households preferences and willingness to pay for various space heating system attributes. We found that in general households prefer renewable sources and systems, but avoid wood. Preferences for familiar technologies have a considerable impact on the probabilities of choice and could represent a significant obstacle to the development of energy-ecient equipment. Willingness to pay for attributes that control energy consumption depends on thermal comfort preferences. The more cold-sensitive the household, the more willing it is to invest to renewable energy sources and to set temperature management. At the first time we modeling the household utility function derived from thermal comfort (annual space heating service) which is a strictly increasing and concave function of indoor temperature. The households can obtain additional utility from energy efficiency after the dwelling renovation. This renovation allows not only to reach the thermal comfort at least cost, but also to enjoy the advantages of new installation as a brand, type of heating system, internal or external solid wall insulation, type of heat emitters, energy source (natural gas, electricity, wood, etc.), control system to manage set temperature of space heating, etc. The utility, derived from retrofit works, is a function of purchase attributes and constant over time. The households choose the level of indoor temperature and decide to invest in retrofit works in order to maximize their utility, subject to available income which is sufficient to cover energy bills. We use annual degree heating days, function of indoor temperature, to calculate energy bills. Household and firm are supposed to be risk averse. In order to analyze household preferences for energy efficiency works, we adapt the econometric approach based on the Random Utility Model (RUM), also known as discrete choice analysis. The random utility function is decomposed in two parts. One is observable by the researcher and can be estimated, the other one is considered to be random. The RUM allows us to obtain the probability to invest in different retrofit works. Data At the beginning of January 2015 a sample of 2000 respondents is collected by internet from a panel of 600,000 French Households. The survey consists of two parts (revealed preferences data and two choice experiments) and contains questions about socio-economic and demographic information, dwelling conditions, energy attitudes, space heating system and thermal comfort. We uses a balancing orthogonal fractional factorial design with main effects only to design the choice experiments. In the first choice experiment, the respondent must take a choice between three offers of space heating systems in order to replace the old system which is broken down. The offers are characterized by the following attributes: investment cost, expected energy-savings potential, energy used, type of space heating system, guarantee period, control system to manage set temperature, financial grant and bank loan. In the second choice experiment, we propose to improve energy efficiency of respondent’s dwelling. The respondent must choose between three offers: install new space heating system, insulate walls and roof, to do both. Or the respondent can decide do not invest in retrofits works. The offers’ attributes are the same as in first choice situation. We expect that the study will provide us the information about different thermal comfort profile of French households (most preferred indoor temperature, causes of discomfort). The choices situations will used to find the willingness to pay and reservation prices for energy efficiency works. The program of contract between household and firm will allow us to understand French renovation market and propose some solutions to increase the energy efficiency works, the market share of renewable and environmental friendliness equipment.
    Keywords: France, Energy and environmental policy, Microsimulation models
    Date: 2015–07–01
  2. By: M. Meleddu; C. Detotto; M. Vannini
    Abstract: The aim of this paper is to analyse the willingness to pay of art-goers for the protection and preservation of cultural artefacts. To this purpose, a discrete choice experiment approach is employed. The experiment took place in 2011 during a major exhibition dedicated to the artist Costantino Nivola (1911-1988). His works, especially those based on the novel sand-casting technique, are known worldwide and many of them were produced after he moved from Sardinia (Italy) to the United States (where he lived from 1939 to his death in 1988). Over this period he never cut his ties with his native land. As a result, both the American and the Sardinian culture affect and show up in his works. In this context, the discrete choice experiments allowed us to estimate not only the price that people are prepared to pay for the security of Nivola's artefacts but also the contribution of non-market components, such as identity, to preserve those objects. Accounting for heterogeneity, the empirical findings show that among visitors there is a substantial willingness to partially cover the cost of preserving the cultural heritage, with significant differences related to the characteristics of the collections considered.
    Keywords: Mixed Logit,Identity,Discrete Choice Experiment,cultural heritage
    Date: 2017
  3. By: Sviataslau Valasiuk (Faculty of Economic Sciences, University of Warsaw); Mikołaj Czajkowski (Faculty of Economic Sciences, University of Warsaw); Marek Giergiczny (Faculty of Economic Sciences, University of Warsaw); Tomasz Żylicz (Faculty of Economic Sciences, University of Warsaw); Knut Veisten (Institute of Transport Economics, Oslo); Askill Harkjerr Halse (Institute of Transport Economics, Oslo); Iratxe Landa Mata (Institute of Transport Economics, Oslo); Marine Elbakidze (Swedish University of Agricultural Sciences; Forest-Landscape-Society Network); Per Angelstam (Swedish University of Agricultural Sciences; Forest-Landscape-Society Network)
    Abstract: Landscape restoration can improve functionality of land cover patches as green infrastructure, which is essential to ensure the provision of a diverse range of ecosystem services. However, so far designation of protected areas in Fennoscandia has focused primarily on remnant patches of naturally dynamic forests, and not on landscape level restoration. We applied stated preference methodology to assess citizens’ preferences for forest landscape restoration in a cross-border region primarily managed for the industrial forestry, and – at the same time – hosting the transboundary Fulufjället National Park, shared between Sweden and Norway. There is scope for improving green infrastructure functionality by landscape restoration in adjacent forest areas, and including them into the National Park, which aims at gradual restoration of natural processes. In both countries, 54% and 55% choices made, respectively, indicated willingness to pay for extending the National Park by some area of forest landscape restoration.
    Keywords: stated preference valuation, passive protection, transboundary nature protected areas, naturally dynamics boreal forests, willingness-to-pay
    JEL: Q23 Q28 Q51 Q57 Q58
    Date: 2017
  4. By: Michela Faccioli (The James Hutton Institute, Social, Economic and Geographical Sciences Group); Laure Kuhfuss (School of Geography and Sustainable Development, University of St. Andrews); Mikolaj Czajkowski (University of Warsaw, Department of Economics)
    Abstract: The outcome of a conservation policy is often subject to uncertainty. In stated preference valuation, there is increasing recognition that uncertainty affects preferences for environmental policies. However, there is also poor understanding regarding people’s perception of uncertainty per se and risk attitude. To shed more light on this , we designed a discrete choice experiment and compared preferences for environmental outcomes under climate change across two split samples, each confronted with a scenario where environmental outcomes are presented as either certain or uncertain (i.e. probabilistically) but displaying the same expected results. We fi nd that, for an equal expected outcome, preferences vary between the certain and the uncertain treatment. These results indicate that risk attitudes impact stated preferences for conservation policies under uncertainty and reinforce the idea that uncertainty should be included in stated preference studies to provide more accurate and policy relevant results . Interestingly, we additionally find that risk attitudes appear to be both context- and individual-specific– the effect of uncertainty depends on the magnitude and direction of change of the environmental good and on individual’s socio-demographic characteristics.
    Keywords: Stated preference valuation, uncertainty, risk attitude, climate change, conservation
    JEL: D6 D81 Q20 Q51 Q54
    Date: 2017–03
  5. By: Nick Hanley (School of Geography and Sustainable Development, University of St. Andrews); Oleg Sheremet (School of Geography and Sustainable Development, University of St. Andrews); Martina Bozzola (Agricultural Economics and Policy Group, ETH Zurich, Switzerland); Douglas C. MacMillan (DICE, School of Anthropology and Conservation, University of Kent)
    Abstract: Demand for rhino horn products is the main driver of illegal hunting of African rhinos. Using choice modelling we identify the main drivers of demand and estimate consumer willingness to pay for rhino horn attributes of high policy relevance among Vietnamese users and potential users. We find that wild or semi-wild sourced horn, harvested humanly from least rare species is the most valued among Vietnamese consumers. Furthermore, consumers are willing to pay more for illegally-traded horn, indicating that the international ban on the trade has generated a premium for illegal horn.
    Keywords: Rhino Conservation, Illegal Hunting, Trade in Wildlife Products, Choice Experiments
    JEL: F18 Q27 Q51 Q57
    Date: 2017–03
  6. By: Bartolucci, Francesco; Pigini, Claudia
    Abstract: Strict exogeneity of covariates other than the lagged dependent variable, and conditional on unobserved heterogeneity, is often required for consistent estimation of binary panel data models. This assumption is likely to be violated in practice because of feedback effects from the past of the outcome variable on the present value of covariates and no general solution is yet available. In this paper, we provide the conditions for a logit model formulation that takes into account feedback effects without specifying a joint parametric model for the outcome and predetermined explanatory variables. Our formulation is based on the equivalence between Granger's definition of noncausality and a modification of the Sims' strict exogeneity assumption for nonlinear panel data models, introduced by Chamberlain1982 and for which we provide a more general theorem. We further propose estimating the model parameters with a recent fixed-effects approach based on pseudo conditional inference, adapted to the present case, thereby taking care of the correlation between individual permanent unobserved heterogeneity and the model's covariates as well. Our results hold for short panels with a large number of cross-section units, a case of great interest in microeconomic applications.
    Keywords: fixed effects, noncausality, predetermined covariates, pseudo-conditional inference, strict exogeneity
    JEL: C12 C23 C25
    Date: 2017–03–13
  7. By: Lorenzo Varela , Juan Manuel (KTH); Börjesson, Maria (KTH); Daly, Andrew (ITS, Leeds / RAND Europe)
    Abstract: This paper develops a methodology for testing and implementing differences in preferences for a set of public transport modes, relating to observed and unobserved attributes, in state-of-practice large-scale travel demand models. Results of a case study for commuters in the Stockholm public transport system suggest that there are preference differences among public transport modes, and that they are captured by unobserved attributes. Surprisingly, we found no evidence for differences proportional to the in-vehicle time, suggesting that characteristics of in-vehicle time in different public transport modes, such as comfort, are valued equally by the travellers. We also found that the value of time is higher for auxiliary modes than for the main mode, and that the unobserved preference for metro is highest and the preference for light rail lowest.
    Keywords: Choice behaviour; Generalised travel cost; Unobserved preferences; Rail factor; Demand forecast
    JEL: R40
    Date: 2017–03–23

This nep-dcm issue is ©2017 by Edoardo Marcucci. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.