nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2013‒04‒20
seven papers chosen by
Edoardo Marcucci
Universita' di Roma Tre

  1. Estimation in semiparametric models with missing data By Chen, Songxi
  2. Using choice experiments to improve the design of weed decision support tools By Kragt, Marit Ellen; Llewellyn, Rick S.
  3. Semiparametric duration analysis with an endogenous binary variable: An application to hospital stays By Masuhara, Hiroaki
  4. Allocation of Ordered Exclusive Choices By Marc Sangnier
  5. Ambiguity revealed By Ralph Bayer; Subir Bose; Matthew Polisson; Ludovic Renou
  6. Developing Consistent Marginal Effect Estimates in a Simultaneous Equation Model with Limited Dependent Variables By Atwood, Joseph A.; Bittinger, Alison; Smith, Vincent H.
  7. Risk Aversion Relates to Cognitive Ability: Fact or Fiction? By Andersson, Ola; Tyran, Jean-Robert; Wengström, Erik; Holm, Håkan J.

  1. By: Chen, Songxi
    Abstract: This paper considers the problem of parameter estimation in a general class of semiparametric models when observations are subject to missingness at random. The semiparametric models allow for estimating functions that are non-smooth with respect to the parameter. We propose a nonparametric imputation method for the missing values, which then leads to imputed estimating equations for the finite dimensional parameter of interest. The asymptotic normality of the parameter estimator is proved in a general setting, and is investigated in detail for a number of specific semiparametric models. Finally, we study the small sample performance of the proposed estimator via simulations.
    Keywords: Copulas; imputation; kernel smoothing; missing at random; nuisance function; partially linear model; semiparametric model; single index model.
    JEL: C0 C1 C2 C3 C4 C5 C6 C7 C8 C9 G0
    Date: 2012–12
  2. By: Kragt, Marit Ellen; Llewellyn, Rick S.
    Abstract: The potential for computer-based decision support tools (DSTs) to better inform farm management decisions is well-recognised. However, despite considerable investment in a wide range of tools, the uptake by advisers and farmers remains low. Greater understanding of the demand and the most valued features of decision support tools has been proposed as an important step in improving the impact of DSTs. Using a choice experiment, we estimated the values that Australian farm advisers attach to specific attributes of decision support tools, in this case relating to weed and herbicide resistance management. The surveys were administered during dedicated workshops with participants who give weed management advice to grain growers. Results from various discrete choice models showed that advisers’ preferences differ between private fee-charging consultants, those attached to retail outlets for cropping inputs, and advisers from the public sector. Reliably accurate results were valued, but advisers placed a consistently high value on models with an initial input time of three hours or less, compared to models that are more time demanding. Results from latent class models revealed a large degree of personal preference heterogeneity across advisers. Although the majority of advisers attributed some value to the capacity for DST output that is specific to individual paddocks, approximately one quarter of respondents preferred generic predictions for the district rather than greater specificity. The use of a novel non-market valuation approach can help to inform development of decision support tools with attributes valued by potential users.
    Keywords: Decision support, Weed management, Herbicide resistance, Adoption, Agriculture, Choice Modelling, Agribusiness, Farm Management, Research and Development/Tech Change/Emerging Technologies, Q19, Q51,
    Date: 2013–03–29
  3. By: Masuhara, Hiroaki
    Abstract: Background: In duration analysis, we find situations where covariates are simultaneously determined along with the duration variable. Moreover, although the models based on a hazard rate do not explicitly assume heterogeneity, in applied econometrics, the possibility of omitted variables is inevitable and controlling population heterogeneity alone is inadequate. It is important to consider both heterogeneity and endogeneity in duration analysis. Objectives and methods: Explicitly assuming semiparametric correlated heterogeneity, this paper proposes an alternative robust duration model with an endogenous binary variable that generalizes the heterogeneity of both duration and endogeneity using Hermite polynomials. Under these setups, we investigate the difference between the endogenous binary variable's coefficients of the parametric and semiparametric models using the Medical Expenditure Panel Survey (MEPS) data. Results: The parameter values of the endogenous binary variable (insurance choice) are statistically significant at the 1% level; however, the values differ among the parametric and semiparametric models and the any type of insurance choice increases the length of hospital stays by 104.010% in the censored parametric model, and 182.074% in the censored semiparametric model. Compared with the parametric model, the increase of hospital stays in the semiparametric model is large. Moreover, we find that the semiparametric model a twin-peak distribution and that the contour lines differ from the usual ellipsoids of the bivariate normal density. Conclusions: When applied to the duration of hospital stays of the MEPS data, the estimated results of the semiparametric model shows a good performance. The absolute values of the endogenous binary regressor coefficients of the semiparametric models are larger than that of the parametric model. The parametric model underestimates the effect of the individual's insurance choice in our example. Moreover, the estimated densities of the semiparametric models have twin peak distribution.
    Keywords: Endogenous switching, duration analysis, probit, semi-nonparametric model, heterogeneity
    JEL: C14 C31 C34
    Date: 2013–03
  4. By: Marc Sangnier (Aix-Marseille University (Aix-Marseille School of Economics), CNRS & EHESS)
    Abstract: This note describes the Stata command alloch which helps to allocate exclusive choices among individuals who have ordered preferences over available alternatives.
    Keywords: alloch, random allocation, choice criterion
    Date: 2013–04
  5. By: Ralph Bayer; Subir Bose; Matthew Polisson (Institute for Fiscal Studies and University of Leicester); Ludovic Renou
    Abstract: We derive necessary and sufficient conditions for data sets composed of state-contingent prices and consumption to be consistent with two prominent models of decision making under uncertainty: variational preferences and smooth ambiguity. The revealed preference conditions for subjective expected utility, maxmin expected utility, and multiplier preferences are characterised as special cases. We implement our tests on data from a portfolio choice experiment.
    Keywords: ambiguity, expected utility, maxmin, revealed preference, smooth, uncertainty, variational
    JEL: D1 D8
    Date: 2013–03
  6. By: Atwood, Joseph A.; Bittinger, Alison; Smith, Vincent H.
    Abstract: We demonstrate that Theil-type variance corrections are required to obtain consistent marginal effect estimates in Nelson-Olsen's two-stage limited dependent variable (2SLDV) model. As Theil's residuals-based corrections are infeasible with 2SLDV, we present variance correction procedures shown to be virtually equivalent to Theil’s 2SLS corrections for continuous models but that are implementable in 2SLDV models. Simulations demonstrate that the proposed variance correction procedures generate consistent marginal effect estimates. The effects of the correction procedures are illustrated in a study of technology adoption by Ethiopian farmers. Components of the variance correction procedures should prove useful in other applications involving limited dependent variables.
    Keywords: Simultaneous Equation Model, Limited Dependent Variable, Discrete Choice, Theil Correction, Research Methods/ Statistical Methods,
    Date: 2013–03
  7. By: Andersson, Ola (Research Institute of Industrial Economics (IFN)); Tyran, Jean-Robert (Department of Economics, University of Vienna); Wengström, Erik (Department of Economics, Lund University); Holm, Håkan J. (Department of Economics, Lund University)
    Abstract: Recent experimental studies suggest that risk aversion is negatively related to cognitive ability. In this paper we report evidence that this relation might be spurious. We recruit a large subject pool drawn from the general Danish population for our experiment. By presenting subjects with choice tasks that vary the bias induced by random choices, we are able to generate both negative and positive correlations between risk aversion and cognitive ability. Structural estimation allowing for heterogeneity of noise yields no significant relation between risk aversion and cognitive ability. Our results suggest that cognitive ability is related to random decision making, rather than to risk preferences.
    Keywords: Risk preference; cognitive ability; experiment; noise
    JEL: C81 C91 D12 D81
    Date: 2013–04–12

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.