Discrete Choice Models
http://lists.repec.org/mailman/listinfo/nep-dcm
Discrete Choice Models
2019-02-18
Nonparametric maximum likelihood methods for binary response models with random coefficients
http://d.repec.org/n?u=RePEc:ifs:cemmap:65/18&r=dcm
Single index linear models for binary response with random coefficients have been extensively employed in many econometric settings under various parametric specifications of the distribution of the random coefficients. Nonparametric maximum likelihood estimation (NPMLE) as proposed by Cosslett (1983) and Ichimura and Thompson (1998), in contrast, has received less attention in applied work due primarily to computational diffi culties. We propose a new approach to computation of NPMLEs for binary response models that signi cantly increase their computational tractability thereby facilitating greater exibility in applications. Our approach, which relies on recent developments involving the geometry of hyperplane arrangements, is contrasted with the recently proposed deconvolution method of Gautier and Kitamura (2013). An application to modal choice for the journey to work in the Washington DC area illustrates the methods.
Jiaying Gu
Roger Koenker
2018-11-21
Selling Wine In Downtown: Who Is The Urban Winery Consumer?
http://d.repec.org/n?u=RePEc:tbs:wpaper:19-003&r=dcm
Urban tasting rooms are a relatively new and growing phenomenon in the U.S. wine market. However, there has been little research concerning the specific marketing strategies that contribute to the success of urban wineries, including their desired target markets. The current study is an initial attempt to explore consumers’ choices of urban wineries. Based on the data obtained through an online survey (N = 1,412) incorporating a discrete choice experiment (DCE) with visual simulations, the study offers a profile of the urban winery consumer. Managerial implications, limitations, and suggestions for future research are included.
Natalia Velikova
Phatima Mamardashvili
Tim H. Dodd
Matthew Bauman
urban winery; consumer profile; discrete choice experiment
2019
Marginal Compensated Effects in Discrete Labor Supply Models
http://d.repec.org/n?u=RePEc:ces:ceswps:_7493&r=dcm
This paper develops analytic results for marginal compensated effects of discrete labor supply models, including Slutsky equations. It matters, when evaluating marginal compensated effects in discrete choice labor supply models, whether one considers wage increase (right marginal effects) or wage decrease (left marginal effects). We show how the results obtained can be used to calculate the marginal cost of public funds in the context of discrete labor supply models. Subsequently, we use the empirical labor supply model of Dagsvik and Strøm (2006) to compute numerical compensated (Hicksian) and uncompensated marginal (Marshallian) effects resulting from wage changes. The mean Hicksian labor supply elasticities are larger than the Marshallian, but the difference is small.
John K. Dagsvik
Steinar Strøm
Marilena Locatelli
Slutsky equations, discrete choice labor supply
2019
Nonlinear factor models for network and panel data
http://d.repec.org/n?u=RePEc:ifs:cemmap:38/18&r=dcm
Factor structures or interactive effects are convenient devices to incorporate latent variables in panel data models. We consider fixed effect estimation of nonlinear panel single-index models with factor structures in the unobservables, which include logit, probit, ordered probit and Poisson specifi cations. We establish that fi xed effect estimators of model parameters and average partial effects have normal distributions when the two dimensions of the panel grow large, but might suffer of incidental parameter bias. We show how models with factor structures can also be applied to capture important features of network data such as reciprocity, degree heterogeneity, homophily in latent variables and clustering. We illustrate this applicability with an empirical example to the estimation of a gravity equation of international trade between countries using a Poisson model with multiple factors.
Mingli Chen
Ivan Fernandez-Val
Martin Weidner
Panel data, network data, interactive fixed effects, factor models, bias correction, incidental parameter problem, gravity equation
2018-07-03
Preserve or retreat? Willingness-to-pay for Coastline Protection in New South Wales
http://d.repec.org/n?u=RePEc:arx:papers:1902.03310&r=dcm
Coastal erosion is a global and pervasive phenomenon that predicates a need for a strategic approach to the future management of coastal values and assets (both built and natural), should we invest in protective structures like seawalls that aim to preserve specific coastal features, or allow natural coastline retreat to preserve sandy beaches and other coastal ecosystems. Determining the most suitable management approach in a specific context requires a better understanding of the full suite of economic values the populations holds for coastal assets, including non-market values. In this study, we characterise New South Wales residents willingness to pay to maintain sandy beaches (width and length). We use an innovative application of a Latent Class Binary Logit model to deal with Yea-sayers and Nay-sayers, as well as revealing the latent heterogeneity among sample members. We find that 65% of the population would be willing to pay some amount of levy, dependent on the policy setting. In most cases, there is no effect of degree of beach deterioration characterised as loss of width and length of sandy beaches of between 5% and 100% on respondents willingness to pay for a management levy. This suggests that respondents who agreed to pay a management levy were motivated to preserve sandy beaches in their current state irrespective of the severity of sand loss likely to occur as a result of coastal erosion. Willingness to pay also varies according to beach type (amongst Iconic, Main, Bay and Surf beaches) a finding that can assist with spatial prioritisation of coastal management. Not recognizing the presence of nay-sayers in the data or recognizing them but eliminating them from the estimation will result in biased WTP results and, consequently, biased policy propositions by coastal managers.
Ali Ardeshiri
Joffre Swait
Elizabeth C. Heagney
Mladen Kovac
2019-02