nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2008‒11‒04
eleven papers chosen by
Philip Yu
Hong Kong University

  1. Standard and Shuffled Halton Sequences in a Mixed Logit Model By Alexander Staus
  2. Stochastic Revealed Preference and Rationalizability By Jan Heufer
  3. A Geometric Measure for the Violation of Utility Maximization By Jan Heufer
  4. Self-selection and Subjective Well-being : Copula Models with an Application to Public and Private Sector Work By Simon Luechinger; Alois Stutzer; Rainer Winkelmann
  5. Detection of local interactions from the spatial pattern of names in France By Keith Head; Thierry Mayer
  6. Accounting for Negative, Zero and Positive Willingness to Pay for Landscape Change in a National Park By Watson, Fiona; Kriström, Bengt; Colombo, Sergio; Hanley, Nick
  7. Measuring the demand for nature-based tourism in Africa: a choice experiment using the "cut-off" approach By Colombo, Sergio; Hanley, Nick; Bush, Glenn
  8. A combinatorial optimisation approach to non-market environmental benefit aggregation By O'Donoghue, Cathal; Hanley, Nick; Hynes, Stephen
  9. Willingness-to-Pay for Energy Conservation and Free-Ridership on Subsidization – Evidence from Germany By Peter Grösche; Colin Vance
  10. Do High Oil Prices Matter? – Evidence on the Mobility Behavior of German Households By Manuel Frondel; Colin Vance
  11. Labour Supply Modelling in Italy When Minimum Income Scheme is an Option By Narazani E; Shima I

  1. By: Alexander Staus (Institute for Agricultural Policy and Agricultural Markets, University of Hohenheim)
    Abstract: Modeling consumer choice in different areas has lead to an increase use of discrete choice models. Probit or Multinomial Logit Models are often the base of further empirical research of consumer choice. In some of these models the equations to solve have no closed-form expression. They include multi-dimensional integrals which can not be solved analytically. Simulation methods have been developed to approximate a solution for these integrals. This paper describes the Standard Halton sequence and a modification of it, the Shuffled Halton sequence. Both are simulation methods which can reduce computational effort compared to a random sequence. We compare the simulation methods in their coverage of the multi-dimensional area and in their estimation results using data of consumer choice on grocery store formats.
    Keywords: simulation, mixed logit, halton sequence
    JEL: C15 C25
    Date: 2008–09
  2. By: Jan Heufer
    Abstract: This paper explorers rationalizability issues for finite sets of observations of stochastic choice in the framework introduced by Bandyopadhyay et al. (JET, 1999). Is is argued that a useful approach is to consider indirect preferences on budgets instead of direct preferences on commodity bundles. Stochastic choices are rationalizable in terms of stochastic orderings on the normalized price space if and only if there exits a solution to a linear feasibility problem. Together with the weak axiom of stochastic revealed preference the existence of a solution implies rationalizability in terms of stochastic orderings on the commodity space. Furthermore it is shown that the problem of finding sufficiency conditions for binary choice probabilities to be rationalizable bears similarities to the problem considered here.
    Keywords: Stochastic choice, rationalizability, revealed preference, weak axiom of stochastic revealed preference, revealed favorability
    JEL: D11
    Date: 2008–09
  3. By: Jan Heufer
    Abstract: Revealed Preference offers nonparametric tests for whether consumption observations can be rationalized by a utility function. If a consumer is inconsistent with GARP, we might need a measure for the severity of inconsistency. One widely used measure is the Afriat efficiency index (AEI).We propose a new measure based on the extent to which the indifference surfaces intersect the budget hyperplanes. The measure is intuitively appealing and, as a cutoff- rule evaluated by Monte Carlo experiments, performs very well compared to the AEI. The results suggest that the new measure is better suited to capture small deviations from utility maximation.
    Keywords: Consumer choice, efficiency index,GARP, nonparametric tests, revealed preference
    JEL: C14 C60 D11 D12
    Date: 2008–09
  4. By: Simon Luechinger; Alois Stutzer; Rainer Winkelmann
    Abstract: We discuss a new approach to specifying and estimating ordered probit models with endogenous switching, or with binary endogenous regressor, based on copula functions. These models provide a framework of analysis for self-selection in economic well-being equations, where assigment of regressors may be choice based, resulting from well-being maximization, rather than random. In an application to public and private sector job satisfaction, and using data on male workers from the German Socio-Economic Panel, we find that a model based on Frank's copula is preferred over two alternative models with independence and normal copula, respectively. The results suggest that public sector workers are negatively selected.
    Keywords: Ordered probit, switching regression, Frank copula, job satisfaction, German Socio-Economic Panel
    JEL: I31 C23
    Date: 2008
  5. By: Keith Head (Sauder School of Business - University of British Columbia); Thierry Mayer (CES - Centre d'économie de la Sorbonne - CNRS : UMR8174 - Université Panthéon-Sorbonne - Paris I)
    Abstract: Using data on name distributions in 95 French d´epartements observed from 1946 to 2002, we investigate spatial and social mechanisms behind the transmission of parental preferences. Drawing inspiration from recent work on social interactions, we develop a simple discrete choice model that predicts a linear relationship between choices by agents in one location and the choices made in neighboring areas. We explain the shares of parents that give their children Saint, Arabic, and American-type names. In a second exercise we examine the effect of distance between locations on differences in name-type shares. In our last exercise we consider dissimilarity in actual names rather than name-types. Using Manhattan Distances as our metric, we find a steady and substantial decline in the importance of geographic distance. Meanwhile, differences in class and national origins have increasing explanatory power.
    Date: 2008
  6. By: Watson, Fiona; Kriström, Bengt; Colombo, Sergio; Hanley, Nick
    Abstract: In contingent valuation, despite the fact that many externalities manifest themselves as costs to some and benefits to others, most studies restrict willingness to pay to being non-negative. In this paper, we investigate the impact of allowing for negative, zero and positive preferences for prospective changes in woodland cover in two UK national parks, the Lake District and the Trossachs. An extended spike model is used to accomplish this. The policy implications of not allowing for negative values in terms of aggregate benefits are also investigated, by comparing the extended spike model with a simple spike making use of only zero and positive bids, and a model which considers positive bids only. We find that ignoring negative values over-states the aggregate benefits of a woodland planting project by up to 44%.
    Keywords: spike models; negative WTP; national parks; contingent valuation
    Date: 2008–06
  7. By: Colombo, Sergio; Hanley, Nick; Bush, Glenn
    Abstract: Integrated Conservation and Development Plans (ICDPs) have been put forward as means of reconciling wildlife conservation in developing countries with improvements in community incomes. In this paper, we use the Choice Experiment approach to quantify overseas tourists' willingness to pay for attributes of nature-based tourism as part of an ICDP, focussing on visits to mountain gorilla areas in Rwanda. Contributions to community incomes are included as one attribute of the design. Methodologically, we employ a "cut-offs" approach to choice modelling to filter inconsistent responses and to reduce hypothetical market bias. Three major findings are that (i) many people choose options which violate their stated maximum trip price (ii) the cut-offs approach changes parameter estimates and thus willingness to pay estimates; and that (ii) that tourists do not have a significant demand for how much of tourism spending is channelled to local communities.
    Keywords: hypothetical market bias; mountain gorillas; Rwanda; cut-offs; choice experiments; nature-based tourism
    Date: 2008–06
  8. By: O'Donoghue, Cathal; Hanley, Nick; Hynes, Stephen
    Abstract: This paper considers the use of spatial microsimulation in the aggregation of regional environmental benefit values. The developed spatial microsimulation model uses simulated annealing to match the Irish Census of Agriculture data to a Contingent Valuation Survey that contains information on Irish farmers' willingness to pay (WTP) to have the corncrake restored as a common sight in the Irish countryside. We then use this matched farm survey and Census information to produce regional and national total WTP figures, and compare these to figures derived using more standard approaches to calculating aggregate environment benefit values. The main advantage of the spatial microsimulation approach for environmental benefit value aggregation is that it allows one to account for the heterogeneity in the target population. Results indicate that the microsimulation modelling approach provides aggregate WTP estimates of a similar magnitude as those produced using the usual sample mean WTP aggregation at the national level, but yields regional aggregate values which are significantly different.
    Keywords: corncrake conservation; willingness to pay; aggregation spatial microsimulation; Environmental benefit value
    Date: 2008–06
  9. By: Peter Grösche; Colin Vance
    Abstract: Understanding the determinants of home-efficiency improvements is significant to a range of energy policy issues, including the reduction of fossil fuel use and environmental protection.This paper analyzes retrofit choices by assembling a unique data set merging a nationwide household survey from Germany with regional data on wages and construction costs. To explore the influence of both heterogeneous preferences and correlation among the utility of alternatives, conditional-, random parameters-, and error components logit models are estimated that parameterize the influence of costs, energy savings,and household-level socioeconomic attributes on the likelihood of undertaking one of 16 renovation options.We use the model coefficients to derive household-specific marginal willingness-to-pay estimates, and with these assess the extent to which free-ridership may undermine the effectiveness of recently implemented programs that subsidize the costs of retrofits.
    Keywords: Heterogenous preferences, residential sector, revealed-preference data
    JEL: C25 D12 Q4
    Date: 2008–08
  10. By: Manuel Frondel; Colin Vance
    Abstract: Focusing on travel survey data from Germany, this paper investigates the determinants of automobile travel, with the specific aim of quantifying the effects of fuel prices and fuel economy. The analysis is predicated on the notion that car mileage is a two-stage decision process, comprising the discrete choice of whether to own a car and the continuous choice of distance traveled. To capture this process, we employ censored regression models consisting of Probit and OLS estimators, which allows us to gauge the extent to which sample selectivity may bias the results. Our elasticity estimates indicate a significant positive association between increased fuel economy and increased driving, and a significantly negative fuel-price elasticity, which ranges between –35% and –41%.Taken together, these results suggest that fuel taxes are likely to be a more effective policy measure in reducing emissions than fuelefficiency standards.
    Keywords: Automobile travel, rebound effect, two-part model
    JEL: D13 Q41
    Date: 2008–10
  11. By: Narazani E; Shima I
    Abstract: In this paper we analyze the effects of Minimum Guaranteed Income (MGI) schemes on labour supply of Italian married couples by applying a behavioural micro-simulation tax-benefit model. The Tax-Benefit Model applied is the static micro-simulation model of EUROMOD. A household labour supply model is simulated with different tax rules where MGI is an option. The simulated tax regimes are Negative Income Tax (NIT), Workfare Tax (WF) and Universal Basic Income (UBI). These exercises of behavioural micro-simulation tax-benefit are performed at national and regional level. Our main finding is that changes in labour supply due to these tax-transfer rules are small and this is in favour of such income support policies. Concerning tax-transfer rules without hour’s constraint, such as UBI and NIT, they imply labour disincentives more in the South than in the North of the country, and the effect is amplified with the increase of generosity level. Considering the welfare effects of these tax-transfer rules, we find that there are more “winners” than “losers” in the south than in the north as there are more households participating in these MGI schemes due to their low income status.
    Keywords: Labour Supply, Discrete Choice Model, Minimum Guaranteed Income, Regional Differences
    JEL: C25 H24 H31 I38
    Date: 2008–07

This nep-dcm issue is ©2008 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.