nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2013‒05‒24
eleven papers chosen by
Edoardo Marcucci
Universita' di Roma Tre

  1. Labelling effects in discrete choice experiments By Doherty, Edel; Campbell, Danny; Hynes, Stephen; van Rensburg, Thomas
  2. Exploring cost heterogeneity in recreational demand By Doherty, Edel; Campbell, Danny; Hynes, Stephen
  3. Estimating Bayesian Decision Problems with Heterogeneous Priors* By Stephen Hansen; Michael McMahon
  4. Investigating Scale Heterogeneity in Latent Class Models By Boeri, Marco; Doherty, Edel; Campbell, Danny; Longo, Alberto
  5. A Nested Logit Model of Green Electricity Consumption in Western Australia By Ma, Chunbo; Burton, Michael
  6. Accounting for Cultural Dimensions in Estimating the Value of Coastal Zone Ecosystem Services using International Benefit Transfer By Hynes, Stephen; Norton, Daniel; Hanley, Nick
  7. Panel Travel Cost Count Data Models for On-Site Samples that Incorporate Unobserved Heterogeneity with Respect to the Impact of the Explanatory Variables By Hynes, Stephen; Greene, William
  8. Do Financially Constrained Firms Suffer from More Intense Competition by the Informal Sector? Firm-Level Evidence from the World Bank Enterprise Surveys By Julia Friesen; Konstantin Wacker
  9. Bayesian Model Averaging for Generalized Linear Models with Missing Covariates By Valentino Dardanoni; Giuseppe De Luca; Salvatore Modica; Franco Peracchi
  10. Do household surveys give a coherent view of disability benefit targeting? A multi-survey latent variable analysis for the older population in Great Britain By Hancock, Ruth; Morciano, Marcello; Pudney, Stephen; Zantomio, Francesca
  11. Binary Choice Models with Discrete Regressors: Identification and Misspecification By Tatiana Komarova

  1. By: Doherty, Edel; Campbell, Danny; Hynes, Stephen; van Rensburg, Thomas
    Abstract: Discrete choice experiment data aimed at eliciting the demand for recreational walking trails on farmland in Ireland is used to explore whether some respondents reach their choices solely on the basis of the alternative’s label. To investigate this type of processing strategy, this paper exploits a discrete mixtures approach that also encompasses continuous distributions to reflect the heterogeneity in preferences for the attributes. We find evidence that a proportion of respondents adopt this processing strategy and that the strategies employed by rural and urban respondents are somewhat different. Results further highlight that model fit and measures of welfare are sensitive to assumptions related to processing strategies among respondents.
    Keywords: Discrete choice, discrete mixtures approach, Environmental Economics and Policy, Land Economics/Use,
    Date: 2012
  2. By: Doherty, Edel; Campbell, Danny; Hynes, Stephen
    Abstract: Farmland can confer significant public good benefits to society aside from its role in agricultural production. In this paper we investigate preferences of rural residents for the use of farmland as a recreational resource. In particular we use the choice experiment method to determine preferences for the development of farmland walking trails. Our modelling approach is to use a series of mixed logit models to assess the impact of alternative distributional assumptions for the cost coefficient on the welfare estimates associated with the provision of the trails. Our results reveal that using a mixture of discrete and continuous distributions to represent cost heterogeneity leads to a better model fit and lowest welfare estimates. Our results further reveal that Irish rural residents show positive preferences for the development of farmland walking trails in the Irish countryside.
    Keywords: Land use, mixed logit models, Environmental Economics and Policy, Land Economics/Use,
    Date: 2012
  3. By: Stephen Hansen; Michael McMahon
    Abstract: In many areas of economics there is a growing interest in how expertise and preferences drive individual and group decision making under uncertainty. Increasingly, we wish to estimate such models to quantify which of these drive decision making. In this paper we propose a new channel through which we can empirically identify expertise and preference parameters by using variation in decisions over heterogeneous priors. Relative to existing estimation approaches, our Prior Based Identication" extends the possible environments which can be estimated, and also substantially improves the accuracy and precision of estimates in those environments which can be estimated using existing methods.
    Keywords: Bayesian decision making; expertise; preferences; estimation
    JEL: D72 D81 C13
    Date: 2013–04
  4. By: Boeri, Marco; Doherty, Edel; Campbell, Danny; Longo, Alberto
    Abstract: This paper develops and compares two alternative approaches to accommodate scale heterogeneity (also referred to as heteroskedasticity) in latent class models. Our modelling approach compares two different representations of heteroskedasticity, respectively associating the heterogeneity in scale factor with respondent's characteristics (i.e. observed scale heterogeneity) or deriving it probabilistically (i.e. unobserved scale heterogeneity). The results reveal a number of benefits associated with this type of approach, particularly when heterosckedasticity can be linked to observed characteristics of the respondent. Our data comes from a discrete choice experiment eliciting recreational users preferences for farmland walking trails in Ireland
    Keywords: Heterogeneity, Heteroskedasticity, Environmental Economics and Policy, Research Methods/ Statistical Methods,
    Date: 2012
  5. By: Ma, Chunbo; Burton, Michael
    Abstract: Green electricity products are increasingly made available to consumers in many countries in an effort to address a number of environmental and social concerns. Most of the existing literature on this green electricity market focuses on consumer’s characteristics and product attributes that could affect participation. However, the contribution of this environmental consumerism to the overall environmental good does not depend on participation alone. The real impact made relies on market penetration for green consumers (the proportion of green consumers) combined with the level of green consumption intensity – the commitment levels, or proportion of consumption that is green. We design an online interface that closely mimics the real market environment for electricity consumers in Western Australia and use a three-level nested logit model to analyze consumers’ choice of green electricity products as well as their commitment levels. Our main conclusions are that the choice of green products is strongly influenced by beliefs in the nature of climate change, and trust in the government and utilities in delivering the product. When green products are selected, the vast majority select the minimum commitment possible, and this is insensitive to the premium being charged on green power, suggesting that we are largely observing a ‘warm glow’ for carbon mitigation
    Keywords: Green Power, Nested Logit, Warm Glow, Green Electricity, Environmental Economics and Policy, Institutional and Behavioral Economics, Resource /Energy Economics and Policy,
    Date: 2013–04–26
  6. By: Hynes, Stephen; Norton, Daniel; Hanley, Nick
    Abstract: Values for non-market goods can be expected to be sensitive to variations in the cultural contexts of beneficiaries. However, little progress has been made to date in adapting benefit transfer procedures for cultural variations. Using information from a study that ranked 62 societies with respect to nine attributes of their cultures, we develop an index that is then used to re-weight multiple coastal ecosystem service value estimates. We examine whether these culturally-adjusted Benefit Transfer (BT) estimates are statistically different than simply transferring the income-adjusted mean transfer estimates for each coastal ecosystem service from international study sites to the policy site. We find that once differences in income levels have been accounted for, the differences in cultural dimensions between study and policy sites actually have little impact on the magnitude of our transfer estimates. This is not a surprising result given that the majority of the study site estimates are derived from countries that share many ethnic, linguistic and other cultural similarities to the policy site. However, benefit adjustments based on cultural factors could have a much higher impacts in settings different to that investigated here.
    Keywords: Non-market goods, Benefit Transfer, coastal ecosystem service, Environmental Economics and Policy, Research Methods/ Statistical Methods, Resource /Energy Economics and Policy,
    Date: 2012
  7. By: Hynes, Stephen; Greene, William
    Abstract: In this paper, we examine heterogeneity in the trip preferences of recreationists by applying a random parameters negative binomial model and a latent class negative binomial model to a panel data set of beach users at a site on the west coast of Ireland. This is the first such attempt in the literature to account for heterogeneity with respect to the impact of the chosen explanatory variables in contingent behaviour travel cost models of demand where the researcher also must account for the fact that the sample data has been collected on-site. The analysis also develops individual consumer surplus estimates and finds that estimates are systematically affected by both the random parameter and latent class specifications. There is also evidence that accounting for individual heterogeneity improves the statistical fit of the models and provides a more informative description of the drivers of recreationalist trip behaviour.
    Keywords: Contingent behaviour, travel cost, count data, heterogeneity, latent class, random parameter, endogenous stratification, truncation, negative binomial, consumer surplus, Environmental Economics and Policy, Research Methods/ Statistical Methods,
    Date: 2012
  8. By: Julia Friesen (Georg-August-University Göttingen); Konstantin Wacker (Vienna University of Economics and Business)
    Abstract: This paper investigates which firms suffer from informal competition and highlights the role of access to finance in this context. We use cross-sectional data from the World Bank Enterprise Surveys covering 42,000 firms in 114 developing and transition countries for the period 2006 to 2011 and take discrete responses on the perceived severity of financial constraints and informal competition for our empirical analysis. We find that financially constrained firms face significantly more intense competition by the informal sector and that this effect is economically large. In fact, financial constraints are the most important reason why firms suffer from informal competition. Other influential variables are ill-designed labor market regulations, corruption, and firm size. A wide range of robustness checks substantiates this finding.
    Keywords: Firm finance; informal competition; enterprise survey data; ordered logit model
    JEL: C25 D21 O17
    Date: 2013–05–21
  9. By: Valentino Dardanoni (University of Palermo); Giuseppe De Luca (University of Palermo); Salvatore Modica (University of Palemo); Franco Peracchi (University of Rome "Tor Vergata" and EIEF)
    Abstract: We address the problem of estimating generalized linear models (GLMs) when the outcome of interest is always observed, the values of some covariates are missing for some observations, but imputations are available to fill-in the missing values. Under certain conditions on the missing-data mechanism and the imputation model, this situation generates a trade-off between bias and precision in the estimation of the parameters of interest. The complete cases are often too few, so precision is lost, but just filling-in the missing values with the imputations may lead to bias when the imputation model is either incorrectly specified or uncongenial. Following the generalized missing-indicator approach originally proposed by Dardanoni et al. (2011) for linear regression models, we characterize this bias-precision trade- off in terms of model uncertainty regarding which covariates should be dropped from an augmented GLM for the full sample of observed and imputed data. This formulation is attractive because model uncertainty can then be handled very naturally through Bayesian model averaging (BMA). In addition to applying the generalized missing-indicator method to the wider class of GLMs, we make two extensions. First, we propose a block-BMA strategy that incorporates information on the available missing-data patterns and has the advantage of being computationally simple. Second, we allow the observed outcome to be multivariate, thus covering the case of seemingly unrelated regression equations models, and ordered, multinomial or conditional logit and probit models. Our approach is illustrated through an empirical application using the first wave of the Survey on Health, Aging and Retirement in Europe (SHARE).
    Date: 2013
  10. By: Hancock, Ruth; Morciano, Marcello; Pudney, Stephen; Zantomio, Francesca
    Abstract: We compare three major UK surveys, BHPS, FRS and ELSA, in terms of the picture they give of the relationship between disability and receipt of the Attendance Allowance (AA) benefit. Using the different disability indicators available in each survey, we estimate a model in which probabilities of receiving AA depend on latent disability status. Despite major differences in design, once sample composition is standardised through statistical matching, the surveys deliver similar results for the model of disability incidence and AA receipt. Provided surveys offer a sufficiently wide range of disability indicators, the detail of disability measurement appears relatively unimportant.
    Date: 2013–05–07
  11. By: Tatiana Komarova
    Abstract: In semiparametric binary response models, support conditions on the regressors are required to guarantee point identification of the parameter of interest. For example,one regressor is usually assumed to have continuous support conditional on the other regressors. In some instances, such conditions have precluded the use of these models; in others, practitioners have failed to consider whether the conditions are satisfied in their data. This paper explores the inferential question in these semiparametric models when the continuous support condition is not satisfied and all regressors have discrete support. I suggest a recursive procedure that finds sharp bounds on the components of the parameter of interest and outline several applications, focusing mainly on the models under the conditional median restriction, as in Manski (1985). After deriving closed-form bounds on the components of the parameter, I show how these formulas can help analyze cases where one regressor's support becomes increasingly dense. Furthermore, I investigate asymptotic properties of estimators of the identification set. I describe a relation between the maximum score estimation and support vector machines and also propose several approaches to address the problem of empty identification sets when a model is misspecified. Finally, I present a Monte Carlo experiment and an empirical illustration to compare several estimation techniques.
    Keywords: Binary response models, Discrete regressors, Partial identification, Misspecification,Support vector machines
    JEL: C2 C10 C14 C25
    Date: 2012–05

This nep-dcm issue is ©2013 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.