nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2008‒12‒21
five papers chosen by
Philip Yu
Hong Kong University

  1. Modelling preference heterogeneity in stated choice data: an analysis for public goods generated by agriculture By Colombo, Sergio; Hanley, Nick; Louviere, Jordan
  2. Can Median-Maximizing Behavior Be Rational? By Vivek Dehejia; Jiankang Zhang
  3. Sequential Estimation of Structural Models with a Fixed Point Constraint By Hiroyuki Kasahara; Katsumi Shimotsu
  4. A Meta-Analysis of Contingent Valuation Studies in Coastal and Near-Shore Marine Ecosystems By Shuang Liu; David I Stern
  5. A Meta-Analysis of the Robustness of Market Size and Labour Cost Determinants of FDI By Simona Rasciute; Eric J Pentecost

  1. By: Colombo, Sergio; Hanley, Nick; Louviere, Jordan
    Abstract: Stated choice models based on the random utility framework are becoming increasingly popular in the applied economics literature. The need to account for respondents' preference heterogeneity in such models has motivated researchers in agricultural, environmental, health and transport economics to apply random parameter logit and latent class models. In most of the published literature these models incorporate heterogeneity in preferences through the systematic component of utility. An alternative approach is to investigate heterogeneity through the random component of utility, and covariance heterogeneity models are one means of doing this. In this paper we compare these alternative ways of incorporating preference heterogeneity in stated choice models and evaluate how the selection of approach affects welfare estimates in a given empirical application. We find that a Latent Class approach fits our data best but all the models perform well in terms of out-of-sample predictions. Finally, we discuss what criteria a researcher can use to decide which approach is most appropriate for a given data set.
    Keywords: choice experiments; covariance heterogeneity model; agri-environmental policy; landscape values; latent class model; preference heterogeneity; random parameter logit model; error component models; welfare measure s
    Date: 2008–12
  2. By: Vivek Dehejia (Department of Economics, Carleton University); Jiankang Zhang (Department of Economics, Carleton University)
    Abstract: In this note, we consider a perennial problem in single-person choice theory, that is, characterizing choice under uncertainty. In particular, we consider a hypothesis put forward by Joseph Stiglitz (2005), suggesting that median-maximing behavior may be optimal under certain circumstances, and consider how it might best be rationalized within choice theory as it is currently conceived. As is well known, median-maximizing behavior is not generally optimal in the classical VNM framework. Our main result is that it is possible to rationalize the Stiglitz hypothesis in the Machina-Schmeidler (1992) framework of probabilistic sophistication.
    JEL: D81
    Date: 2008–11–03
  3. By: Hiroyuki Kasahara (University of Western Ontario); Katsumi Shimotsu (Queen's University)
    Abstract: This paper considers the estimation problem of structural models for which empirical restrictions are characterized by a fixed point constraint, such as structural dynamic discrete choice models or models of dynamic games. We analyze the conditions under which the nested pseudo-likelihood (NPL) algorithm achieves convergence and derive its convergence rate. We find that the NPL algorithm may not necessarily converge when the fixed point mapping does not have a local contraction property. To address the issue of non-convergence, we propose alternative sequential estimation procedures that can achieve convergence even when the NPL algorithm does not. Upon convergence, some of our proposed estimation algorithms produce more efficient estimators than the NPL estimator.
    Keywords: contraction, dynamic games, nested pseudo likelihood, recursive projection method
    JEL: C13 C14 C63
    Date: 2008–12
  4. By: Shuang Liu; David I Stern (CSIRO Entomology, Australia)
    Abstract: The ecosystem services provided by coastal and near-shore marine systems contribute significantly to human welfare. However, studies that document values of these services are widely scattered in the peer-reviewed literature. We collected 39 contingent valuation papers with 120 observations to conduct the first meta-analysis of the ecosystem service values provided by the coastal and near-shore marine systems. Our results show that over ¾ of the variation in Willingness to Pay (WTP) for coastal ecosystem services could be explained by variables in commodity, methodology, and study quality. We also used the meta-regression model to predict out-of-sample WTPs and the benefit transfer result showed that the overall median transfer error was 57%. Based on such results, one could argue that such meta-analyses can provide useful guidance regarding at least the general magnitudes of welfare effects. However, we also caution against the application of such a result in a broader context of benefit transfer as it is derived from a limited amount of data, and it may suffer from some degree of measurement error, generalization error, and publication selection error. Lastly, we discuss possible ways of minimizing these errors.
    Keywords: ecosystem services, valuation, meta-analysis, coastal
    JEL: Q25 Q51 Q57
    Date: 2008–12
  5. By: Simona Rasciute (Dept of Economics, Loughborough University); Eric J Pentecost (Dept of Economics, Loughborough University)
    Abstract: This paper applies a meta-regression analysis to systematically summarise, integrate and synthesise the results of empirical studies that include market size and labour costs as determinants of FDI. Random effects panel estimation is employed separately for the sample of primary studies that use OLS estimation to analyse the effect of market size and labour costs on FDI and for the sample of primary studies that employ discrete choice models to estimate the effect of market size and labour costs on FDI. A number of factors related to model specifications, dataset characteristics and methodologies in the primary studies explain the variation in the estimated t-statistics of the effect of market size and labour costs on FDI across the studies. Most tests for publication bias indicate that the empirical literature on the effect of market size on FDI favours positive estimates while empirical literature on the effect of labour costs on FDI favours negative estimates. None of the literature, however, favours statistical significance.
    Keywords: meta-regression analysis, foreign direct investment, market size and labour costs, publication bias
    JEL: F21
    Date: 2008–12

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.