nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2010‒07‒17
nine papers chosen by
Philip Yu
Hong Kong University

  1. Does income taxation affect partners’ household chores? By Arthur Van Soest; Elena Stancanelli
  2. Attribute processing in environmental choice analysis: implications for willingness to pay By Campbell, Danny; Lorimer, Victoria; Aravena, Claudia; Hutchinson, George
  3. Comparing the Conventional Stated Preference Valuation Technique with a Prediction Approach. By Yadav, Lava; Van Rensburg, Tom; Kelley, Hugh
  4. Effects of Global Climate Change on Nigerian Agriculture: An Empirical Analysis By Apata, T.G; Ogunyinka, A.I; Sanusi, R.A; Ogunwande, S
  5. Do defaults matter? Willingness to pay to avoid GM food vis-à-vis organic and conventional food in Denmark, Great Britain and Spain. By Costa-Font, Montserrat; Tranter, Richard; Gil, José M; Jones, Philip; Gylling, Morten
  6. Combining discrete and continuous mixing approaches to accommodate heterogeneity in price sensitivities in environmental choice analysis By Campbell, Danny; Doherty, Edel; Hynes, Stephen; van Rensburg, Tom
  7. Reducing Bias from Choice Experiments Estimates in the Demand for Recreation By Longo, Alberto; Rowan, Emma; Hutchinson, W. George
  8. Nature protection in an economically depressed region By Marek Giergiczny; Sviataslau Valasiuk; Tomasz Żylicz
  9. Irregular behaviour in stating preferences for nature protection. A Choice Experiment in Belarus By Marek Giergiczny; Sviataslau Valasiuk; Tomasz Żylicz; Pere Riera

  1. By: Arthur Van Soest (Netspar, Tilburg University); Elena Stancanelli (THEMA Universite Cergy Pontoise)
    Abstract: We study the impact of income taxation on both partners’ allocation of time to market work and unpaid house work in households with two adults. We estimate a structural household utility model in which the marginal utilities of leisure and house work of both partners are modelled as random coefficients, depending on observed and unobserved characteristics of the household and the two partners. We use a discrete choice model with choice sets of 2,401 points for each couple, distinguishing seven market work intervals and seven house work intervals for each partner. The model is estimated using data for France, which taxes incomes of married couples jointly, like, for instance, Germany and the US. We find that both partners’ market and non-market time allocation decisions are responsive to changes in the tax system or other policy changes that change the financial incentives. Women’s time allocation is more responsive to the own and the partner’s wage rate than men’s. Tax policy simulations suggest that moving from joint taxation for married couples to separate taxation of each spouse would go a small step in the direction of equalizing market and non-market work of spouses. Selective taxation with smaller tax rates for women than for men would magnify these effects.
    Keywords: time use, taxation, discrete choice models
    JEL: J22 H31 C35
    Date: 2010–06
  2. By: Campbell, Danny; Lorimer, Victoria; Aravena, Claudia; Hutchinson, George
    Abstract: Data from a discrete choice experiment is used to investigate the implications of failing to account for attribute processing strategies (APSs). The research was designed to elicit the economic benefits associated with landscape restoration activities that were intended to remediate environmental damage caused by illegal dumping activities. In this paper we accommodate APSs using an equality constrained latent class model. By retrieving the conditional class membership probabilities we recover estimates of the weights that each respondent assigned to each attribute, which we subsequently use ensure unnecessary weight is not allocated to attributes not attended to by respondents. Results from the analysis provide strong evidence that significant gains in models fit as well as more defensible and reliable willingness to pay estimates can be achieved using when the APSs are accounted for.
    Keywords: Attribute processing strategies, environmental restoration, equality constrained latent class model, multinomial logit model, willingness to pay, Environmental Economics and Policy,
    Date: 2010–03–29
  3. By: Yadav, Lava; Van Rensburg, Tom; Kelley, Hugh
    Abstract: Stated preference techniques have been used to place values on public goods by directly asking individuals to provide their personal values and opinions. This method has consistently resulted in the emergence of hypothetical bias. Several insights from the psychology literature suggest that social desirability bias, a contributor to hypothetical bias, occurs when individuals face such direct questions. However, replacing the direct questions with an indirect one that asks for their predictions about otherâs values can potentially eliminate this bias. In this study we employ both questioning formats in a choice experiment to make comparisons between the stated responses. Predicted willingness to pay is 2.5 and 3.1 times smaller than hypothetical values indicating predictions to be a more accurate measure of actual values. The study further highlights the vulnerability of the conventional approach to a social desirability bias as it allows normative motives to distort respondentsâ decisions, which in turn generates preferences for environmental attributes that are misleading.
    Keywords: Stated Preference Techniques, Discrete Choice Experiments, Hypothetical Bias, Social Desirability Bias, Lake Wabegon Effect, False Consensus Effect, Willingness to Pay, Environmental Economics and Policy,
    Date: 2010–03–29
  4. By: Apata, T.G; Ogunyinka, A.I; Sanusi, R.A; Ogunwande, S
    Abstract: This paper presents an empirical analysis of the effects of global warming on Nigerian agriculture and estimation of the determinants of adaptation to climate change. Data used for this study are from both secondary and primary sources. The set of secondary sources of data helped to examine the coverage of the three scenarios (1971-1980; 1981-1990 and 1991-2000). The primary data set consists of 1500 respondentsâ but only 1250 cases were useful. This study analyzed determinants of farm-level climate adaptation measures using a Multinomial choice and stochastic-simulation model to investigate the effects of rapid climatic change on grain production and the human population in Nigeria. The model calculates the production, consumption and storage of grains under different climate scenarios over a 10-year scenery. In most scenarios, either an optimistic baseline annual increase of agricultural output of 1.85% or a more pessimistic appraisal of 0.75% was used. The rate of natural increase of the human population exclusive of excess hunger-related deaths was set at 1.65% per year. Results indicated that hunger-related deaths could double if grain productions do not keep pace with population growth in an unfavourable climatic environment. However, Climate change adaptations have significant impact on farm productivity.
    Keywords: Climate change, Adaptation, Economic consequences, Farm level productivity, Average Rainfall, Nigeria, Food Security and Poverty, D6, D91, E21, O13, Q01, Q2,
    Date: 2010–03–29
  5. By: Costa-Font, Montserrat; Tranter, Richard; Gil, José M; Jones, Philip; Gylling, Morten
    Abstract: The introduction and communication of new technologies in the food industries has given rise in the past to some scientific uncertainty that hampers informed choice. Here we draw upon the case of Genetically Modified (GM) technology and, in particular, on different types of GM food, to investigate consumersâ behavioural reactions to GM food as well as their willingness to pay for avoiding GM food in three EU countries, Denmark, GB and Spain in 2007. Our unique contribution lies in that our empirical analysis concerns two food products containing different characteristics. In particular, we compare consumersâ reactions to cornflakes (to represent a processed food) and tomatoes (to represent a 'fresh' food) juxtaposed with GM and conventionally produced food. Our results reveal that, although GM food is the least preferred production process (vis-à-vis organic or conventional food), consumers can be divided into two groups depending on their preferences for organic food. Namely, a first group is made up of GB and Spain where consumers are willing to pay a small, or modest, premium over the respective market average price, and a second group is that of Denmark where consumersâ willingness to pay is significantly larger. Although risk is an influential characteristic, risk rankings indicate that GM food is perceived as less risky than irradiation, artificial growth hormones in food or pesticides used in the production process.
    Keywords: Genetically modified food, consumer behaviour, choice models, Denmark, Grate Britain and Spain., Food Security and Poverty,
    Date: 2010–03–29
  6. By: Campbell, Danny; Doherty, Edel; Hynes, Stephen; van Rensburg, Tom
    Abstract: Data from a discrete choice experiment aimed at eliciting the demand for recreational walking trails on farmland in the Republic of Ireland is used to explore the consequences of misspecifying the cost coeffcient. To enable straightforward calculation of WTP from the distributions of the non-price coeffcients, the price coeffcient is typically held constant in mixed logit models. This implies that all respondents are equally price sensitive. In this paper we test the validity of this assumption. Our approach is based on a comparison and combination of discrete and continuous mixing approaches (i.e., a mixture of distributions) to uncover the unobserved heterogeneity in price sensitivities. Results from the analysis highlight that model fit and willingness to pay are sensitive to the distributional assumptions used to represent the price coeffcient.
    Keywords: Discrete choice experiments, discrete mixtures, continuous mixtures, mixtures of distributions, price sensitivities, farmland recreation, willing to pay space, Environmental Economics and Policy,
    Date: 2010–03–29
  7. By: Longo, Alberto; Rowan, Emma; Hutchinson, W. George
    Abstract: In valuing the demand for recreation, the literature has grown from using revealed preference methods to applying stated preference methods, namely contingent valuation and choice modelling. Recent attempts have merged revealed and stated preference data to exploit the strengths of both sources of data. We use contingent behaviour and choice experiments data to show that, with choice experiments exercises, when respondents are asked to choose which improvement programme they prefer for a site with recreational opportunities, failing to consider the information explaining the number of visits that respondents intend to take to a recreational site under each hypothetical programme leads to biased coefficients estimates in the models for the choice experiments data.
    Keywords: travel cost, contingent behaviour, choice experiments, revealed preferences, stated preferences, Environmental Economics and Policy, Q51, Q26,
    Date: 2010–03–29
  8. By: Marek Giergiczny (Warsaw Ecological Economics Center, University of Warsaw); Sviataslau Valasiuk (Warsaw Ecological Economics Center, University of Warsaw); Tomasz Żylicz (Warsaw Ecological Economics Center, University of Warsaw)
    Abstract: We look at perspectives of nature protection in a wetland of international importance in South-Western part of Belarus. The region is economically depressed, which may prove to be a factor in local conservation initiatives. A theoretical model is developed to identify conditions for the local population to get involved in the fen mire conservation projects. The model is then verified by means of a choice experiment administered in villages neighbouring the site. The main outcome of the valuation experiments is to demonstrate that a carefully designed conservation programme is likely to enjoy the support of the local population who appreciates economic opportunities provided by saving the wetland.
    Keywords: wetlands, biodiversity protection, local development, ecological tourism, choice experiment (CE), random utility model (RUM)
    JEL: Q50 Q51
    Date: 2010
  9. By: Marek Giergiczny (Warsaw Ecological Economics Center, University of Warsaw); Sviataslau Valasiuk (Warsaw Ecological Economics Center, University of Warsaw); Tomasz Żylicz (Warsaw Ecological Economics Center, University of Warsaw); Pere Riera (Faculty of Economic Sciences, University of Warsaw)
    Abstract: Using choice experiment, this paper investigates how Belarusian citizens value planned Zvanets mire protection programmes. Two approaches are used to analyze ignored attributes: a debriefing question, and estimating parameters at the individual level. We have found inconsistencies between people’s declarations on ignoring certain attributes in the follow-up questions and the results of modelling at the individual level. These inconsistencies lead to statistically significant differences in WTP estimates obtained.
    Keywords: willingness to pay (WTP), choice experiment (CE), random parameter logit (RPL) model, lexicographic preferences, nature protection, wetlands
    JEL: Q50 Q51
    Date: 2010

This nep-dcm issue is ©2010 by Philip Yu. 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.