nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2017‒08‒27
three papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. Simulation error in maximum likelihood estimation of discrete choice models By Mikołaj Czajkowski; Wiktor Budziński
  2. The Influence of Scientific Information on the Willingness to Pay for Stormwater Runoff Abatement By Peter A. Groothuis; Tanga A. Mohr; John C. Whitehead; Kristan A. Cockerill; William P. Anderson, Jr.; Chuanhui Gu
  3. Estimating recreational values of coastal zones By Halkos, George; Matsiori, Steriani

  1. By: Mikołaj Czajkowski (Faculty of Economic Sciences, University of Warsaw); Wiktor Budziński (Faculty of Economic Sciences, University of Warsaw)
    Abstract: Maximum simulated likelihood is the preferred estimator of most researchers who deal with discrete choice. It allows estimation of models such as mixed multinomial logit (MXL), generalized multinomial logit, or hybrid choice models, which have now become the state-of-practice in the microeconometric analysis of discrete choice data. All these models require simulation-based solving of multidimensional integrals, which can lead to several numerical problems. In this study, we focus on one of these problems – utilizing from 100 to 1,000,000 draws, we investigate the extent of the simulation bias resulting from using several different types of draws: (1) pseudo random numbers, (2) modified Latin hypercube sampling, (3) randomized scrambled Halton sequence, and (4) randomized scrambled Sobol sequence. Each estimation is repeated up to 1,000 times. The simulations use several artificial datasets based on an MXL data generating process with different numbers of individuals (400, 800, 1200), different numbers of choice tasks per respondent (4, 8, 12) and different experimental designs (D-optimal, D-efficient for the MNL and D-efficient for the MXL model). Our large-scale simulation study allows for comparisons and drawing conclusions with respect to (1) how efficient different types of quasi Monte Carlo simulation methods are and (2) how many draws one should use to make sure the results are of “satisfying” quality – under different experimental conditions. Our study is the first to date to offer such a comprehensive comparison.
    Keywords: discrete choice, mixed logit, simulated maximum log-likelihood function, simulation error, draws, quasi Monte Carlo methods, MLHS, Halton, Sobol, number of draws
    JEL: C15 C51 C63
    Date: 2017
  2. By: Peter A. Groothuis; Tanga A. Mohr; John C. Whitehead; Kristan A. Cockerill; William P. Anderson, Jr.; Chuanhui Gu
    Abstract: We integrated physical science data with a social science survey to better understand people’s preferences for stormwater runoff abatement measures. Data from a long-term monitoring project on Boone Creek in North Carolina revealed that two key concerns from stormwater runoff are thermal pollution and high salinity. We used this data to develop text and images to include in a survey to assess public attitudes about and willingness to pay for stormwater runoff abatement measures in the Appalachian region. The survey provided information about various methods to reduce stormwater runoff including containment systems and permeable pavement. To assess the impact of scientific information on individual preference for stormwater runoff abatement, we randomly assigned different levels of scientific information to survey respondents. Our results show that having more detailed scientific information has two effects. The direct effect is to reduce willingness to pay for runoff abatement programs. Indirectly, the detailed information increases self-reported claims of understanding the information provided and those who claim to understand the information are more likely to be willing to pay for abatement measures. Key Words: stormwater management, stream water quality, scientific communication, stated preferences, willingness to pay
    Date: 2017
  3. By: Halkos, George; Matsiori, Steriani
    Abstract: The present study tries to improve our understanding of why some people value coastal zone using attitudinal and preference factors in a Contingent Valuation Method (CVM) study. Specifically, it aims at public preferences for improving the quality (protection) of Pagasitikos coastal area in Greece and explores the influence of environmental attitude on preference to people’s willingness to pay (WTP) coastal zone conservation. It also presents the results of a discrete CVM survey which investigates households’ WTP for a set of wetland attributes. The proposed approach uses applied methodological methods like Principal Components and Cluster Analyses together with logistic regression. Various demographic variables (as education and income) together with people’s preferences for coastal zone show a strong impact on WTP and the specific amounts stated. At a second stage people who accept the CVM scenario results and grouped into two segments, with different attitude against coastal zone management and ecological view.
    Keywords: Environnemental attitudes; NEP scale; CVM; WTP; coastal zone people perception.
    JEL: C10 C52 Q20 Q50 Q51 Q57
    Date: 2017–08

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.