nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2008‒07‒30
ten papers chosen by
Philip Yu
Hong Kong University

  1. Marginal and Interaction Effects in Ordered Response Models By Mallick, Debdulal
  2. The Location of Foreign Direct Investment in the Central and Eastern European Countries: A Mixed Logit and Multilevel Data Approach By Simona Rasciute; Eric J. Pentecost
  3. 'CHOOSER DEPENDANT' PREFERENCES, AND ATTITUDES de se By Vittorioemanuele Ferrante
  4. What Prompts the People's Bank of China to Change its Monetary Policy Stance? Evidence from a Discrete Choice Model By Dong He; Laurent Pauwels
  5. Better than their reputation - A case for mail surveys in contingent valuation By Michael Ahlheim; Benchaphun Ekasingh; Oliver Frör; Jirawan Kitchaicharoen; Andreas Neef; Chapika Sangkapitux; Nopasom Sinphurmsukskul
  6. Equity and Aggregation in Environmental Valuation By Michael Ahlheim; Ulrike Lehr
  7. Eliciting Biodiversity and Landscape Trade-off in Landscape Projects: Pilot Study in the Anciens Marais des Baux, Provence, France By Robert Lifran; Vanja Westerberg
  8. Rationalization and Cognitive Dissonance: Do Choices Affect or Reflect Preferences? By M. Keith Chen
  9. Revealed Conflicting Preferences By Attila Ambrus; Kareen Rozen
  10. Airport Choice in a Constraint World: Discrete Choice Models and Capacity Constraints By Gelhausen, Marc Christopher

  1. By: Mallick, Debdulal
    Abstract: In discrete choice models the marginal effect of a variable of interest that is interacted with another variable differs from the marginal effect of a variable that is not interacted with any variable. The magnitude of the interaction effect is also not equal to the marginal effect of the interaction term. I present consistent estimators of both marginal and interaction effects in ordered response models. This procedure is general and can easily be extended to other discrete choice models.
    Keywords: Marginal effect; interaction effect; ordered probit
    JEL: C12 C25
    Date: 2008–07
  2. By: Simona Rasciute (Dept of Economics, Loughborough University); Eric J. Pentecost (Dept of Economics, Loughborough University)
    Abstract: This paper uses the Mixed logit (ML) model and a novel three-level dataset to examine the factors explaining 1,108 foreign direct investment (FDI) location decisions into 13 Central and Eastern European countries (CEECs) over an eleven-year period between 1997 and 2007. The ML model approach is superior to other discrete choice methods in that it allows for random taste variation, unrestricted substitution patterns and correlation in unobserved factors over time. The highly significant empirical results, based on a general underlying economic model of imperfect competition, show that the responsiveness of the probabilities of choices to invest in a particular country in CEE to country-level variables differs both across sectors and across firms of different sizes and profitability. The results generalise previous studies that used only country-level data or only industry- and firm-level data to give a more accurate explanation of the firm-specific investment location decisions.
    Keywords: Mixed logit model, random parameters, foreign direct investment, multi-level data, Halton draws
    JEL: F23 P33
    Date: 2008–07
  3. By: Vittorioemanuele Ferrante (Università degli Studi di Firenze, Dipartimento di Scienze Economiche)
    Abstract: Sen’s 'chooser dependence' of preferences generates issues of indexicality which, we claim, can in fact be reduced to a specification of the content of preferences within a standard approach, by means of Lewis’ theory of attitudes de se. While context sensitivity of preferences can be dealt with by the addition to the outcomes of choice of their relevant mereological contexts, indexical sensitivity requires the content of preferences to include (the nature of) the decision maker him/herself. The result is a naturalistic internalization of preferences, which become object of preference, belief, and action. Keywords: Preferences, utility, choice, attitudes, mereology, properties.
    Date: 2008
  4. By: Dong He (Research Department, Hong Kong Monetary Authority); Laurent Pauwels (Research Department, Hong Kong Monetary Authority)
    Abstract: In this paper, we model the policy stance of the People¡¦s Bank of China (PBoC) as a latent variable, and the discrete changes in the reserve requirement ratio, policy interest rates, and the scale of open market operations are taken as signals of movement of this latent variable. We run a discrete choice regression that relates these observed indicators of policy stance to major trends of macroeconomic and financial developments, which are represented by common factors extracted from a large number of variables. The predicted value of the estimated model can then be interpreted as the implicit policy stance of the PBoC. In a second step, we estimate how much of the variation in the PBoC's implicit stance can be explained by measures of its policy objectives on inflation, growth and financial stability. We find that deviations of CPI inflation from an implicit target and deviations of broad money growth from the announced targets figured significantly in PBoC's policy changes, but not output gaps.
    Keywords: Monetary policy, People's Bank of China, qualitative response models, large factor models
    JEL: E52 E58 C25 C32
    Date: 2008–06
  5. By: Michael Ahlheim; Benchaphun Ekasingh; Oliver Frör; Jirawan Kitchaicharoen; Andreas Neef; Chapika Sangkapitux; Nopasom Sinphurmsukskul
    Abstract: Though contingent valuation is the dominant technique for the valuation of public projects, especially in the environmental sector, the high costs of contingent valuation surveys prevent the use of this method for the assessment of relatively small projects. The reason for this cost problem is that typically only contingent valuation studies which are based on face-to-face interviews are accepted as leading to valid results. Especially in countries with high wages face-to-face surveys are extremely costly considering that for a valid contingent valuation study a minimum of 1,000 completed face-to-face interviews is required. In this paper we try a rehabilitation of mail surveys as low-budget substitutes for costly face-to-face surveys. Based on an empirical contingent valuation study in Northern Thailand we show that the validity of mail surveys can be improved significantly if so-called citizen expert groups are employed for a thorough survey design.
    Keywords: contingent valuation; Environmental Valuation; Equity
    JEL: D6 H4 L3 Q25 Q51
    Date: 2008–07
  6. By: Michael Ahlheim; Ulrike Lehr
    Abstract: Environmental valuation studies aim at the assessment of the social benefits or the social costs caused by some change in environmental quality (in the broadest sense). The most popular field of application of environmental valuation studies is project appraisal where the benefits arising from some environmental project (measured in terms of people's willingness to pay for that project) are assessed and confronted with the costs of the project or with the benefits from some alternative project if a choice has to be made between different projects. A closer look at the results of empirical valuation studies shows that in many surveys a negative correlation between the number auf household members and the willingness to pay (WTP) stated by a household for a project can be observed. These results are rather puzzling because in larger households more people are going to benefit from an environmental improvement than in small households. A plausible explanation for these results is that household budgets are tighter for large households than for smaller households with the same household income. Therefore, large households must state a smaller WTP for a project than smaller households with the same income and the same preferences. This might have consequences for the allocation of public funds in all cases where the realization of a specific environmental project depends on the absolute value of the aggregate social benefits it generates. In order to calculate the social benefits typically the WTPs of the different households affected by that project are added up. In this aggregation process the members of larger households have a lower weight and, therefore, their WTP has a smaller impact on the decision if a certain project is realized or not. The reason for this violation of the principle of horizontal equity is that for the computation of the social benefits not individual but household WTPs are aggregated. In this paper we suggest to use household equivalence scales for the evaluation of WTP data in order to reduce this discrimination of the members of large families. We demonstrate the effects of equivalence scales on the results of environmental valuation surveys using an empirical study carried out in Eastern Germany.
    Keywords: contingent valuation; Environmental Valuation; Equity
    JEL: D61 D63 H43 Q51
    Date: 2008–04
  7. By: Robert Lifran; Vanja Westerberg
    Abstract: The purpose of this paper is to elicit social preferences for various organizational and managerial changes in the landscape of the agricultural area called “Ancien Marais des Baux”, at the foothill of the Alpilles Mountain, in Provence. We present preliminaries results from a pilot survey conducted in the area in the winter of 2008. In our research, the environmental resource is the landscape, defined in terms of its attributes and levels these attributes would take with and without various management options. We use the Choice Experiment to determine what the preferred landscape is, and under wetland restoration, the most desired features that the wetland should provide. The random parameter logit model is employed to take into account variances in unobserved preference heterogeneity. Consistent with expectations, we observed that respondents who are neither green, have little attachment to wetlands, have poor understanding of wetland services, are WTP less ceteris paribus for all the attributes in question, compared to the respondents that have green behaviour, knows about wetlands or cares about their existence in Marais des Baux. Not surprisingly, the respondents considering the wetland in Marais des Baux, part of their cultural heritage, wants to visit it in the future, and preserve it for future generations, have the greatest WTP for any combination of attributes. We also observed the importance of mosquito control in any support of wetland restoration among respondents. Indeed, restoration on an advanced scale is only accepted in the presence of biological mosquito control. Distinct landscape features, such as tree hedges which still allows for the view of the massif of the Alpilles are valued equally high as the recreational opportunites related to the wetland. Biodiversity is low on the priority list compared to other attributes, but still positively valued.
    Date: 2008–07
  8. By: M. Keith Chen (Yale University)
    Abstract: Cognitive dissonance is one of the most influential theories in psychology, and its oldest experiential realization is choice-induced dissonance. In contrast to the economic approach of assuming a person's choices reveal their preferences, psychologists have claimed since 1956 that people alter their preferences to rationalize past choices by devaluing rejected alternatives and upgrading chosen ones. Here, I show that every study which has tested this preference-spreading effect has overlooked the potential that choices may reflect individual preferences. Specifically, these studies have implicitly assumed that subject's preferences can be measured perfectly, i.e., with infinite precision. Absent this, their methods, even with control groups, will mistakenly identify cognitive dissonance when there is none. Correctly interpreted, several prominent studies actually reject the presence of choice-induced dissonance. This suggests that mere choice may not always induce rationalization, a reversal that may significantly change the way we think about cognitive dissonance as a whole.
    Keywords: Cognitive dissonance, Revealed preference
    JEL: A12 C91 D01
    Date: 2008–07
  9. By: Attila Ambrus (Harvard University); Kareen Rozen (Cowles Foundation, Yale University)
    Abstract: We model a DM as a collection of utility functions (selves, rationales) and an aggregation rule (a theory of how selves are activated by choice sets). The DM’s choice function is rationalized by a collection of selves and an aggregator if it selects the unique maximizer of aggregate utility. For a general class of aggregators, we show that the number of selves required to rationalize a choice function is at most a linear function of the number of IIA violations exhibited. We provide simple conditions for checking when an aggregator can rationalize all choice functions with enough selves; and provide a minimal set of behaviors that an aggregator can rationalize with a fixed number of selves. We apply the framework to choice over menus and examine the revealed preference implications of IIA violations for the subjec­tive state-space. While consistent with evidence in psychology on multiple selves, our framework also has implications for models of collective house-hold behavior and marketing models of multiattribute goods.
    Keywords: Multiple selves, IIA violations, Context-dependent choice, Rationalizability, Complexity
    JEL: D11 D13 D71
    Date: 2008–07
  10. By: Gelhausen, Marc Christopher
    Abstract: The purpose of this paper is to present a new approach to model capacity constraints in discrete choice with at least some capacity-related variables missing, like e.g. the price of a commodity. Airport choice models often do not contain air fares because of measurement difficulties as air fares are often not included in passenger surveys and thus essential information regarding ticket price is lost to the researcher. Since air fares vary more across ticket categories at an airport than a ticket category varies across different airports, air fare related information cannot be reconstructed in many cases by the researcher. However, capacity constraints are becoming increasingly more important and thus including capacity constraints in airport choice models is reasonable. The model approach is based on individual utility maximisation and thus fits into the discrete choice framework. Furthermore, nonlinear programming is employed to find a feasible solution regarding capacity constraints. Thereby, detailed statements on how limited airport capacity changes traveller behaviour with regard to airport choice on the level of individual air travellers and airports are possible. The paper concludes with an empirical example to demonstrate the methodology and show the impact of limited airport capacity on airport choice of air travellers.
    Keywords: Airport and Access Mode Choice; Capacity Constraints; Choice Behaviour; Discrete Choice; Nonlinear Programming
    JEL: C53 C61 C25
    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.