|
on Discrete Choice Models |
| By: | Didier Nibbering |
| Abstract: | The number of parameters in a standard multinomial choice model increases linearly with the number of choice alternatives and number of explanatory variables. Since many modern applications involve large choice sets with categorical explanatory variables, which enter the model as large sets of binary dummies, the number of parameters easily approaches the sample size. This paper proposes a new method for data-driven parameter clustering over outcome categories and explanatory dummy categories in a multinomial probit setting. A Dirichlet process mixture encourages parameters to cluster over the categories, which favours a parsimonious model specification without a priori imposing model restrictions. An application to a dataset of holiday destinations shows a decrease in parameter uncertainty, an enhancement of the parameter interpretability, and an increase in predictive performance, relative to a standard multinomial choice model. |
| Keywords: | large choice sets, Dirichlet process prior, multinomial probit model, high-dimensional models |
| JEL: | C11 C14 C25 C35 C51 |
| Date: | 2019 |
| URL: | http://d.repec.org/n?u=RePEc:msh:ebswps:2019-19&r=all |
| By: | Jared C.Carbone (Division of Economics and Business, Colorado School of Mines); Sul-Ki Lee (Korean Institute for Industrial Economics and Trade); Yuzhou Shen (Division of Economics and Business, Colorado School of Mines) |
| Abstract: | We estimate household demand for climate amenities in the United States with two main objectives in mind: (i) to estimate model parameters with the demographic detail needed to inform climate-induced migration responses in regional population projections for use in climate impact analysis; (ii) to study the robustness of estimates from the existing literature. With respect to the former goal, we find important differences in job-related migration motives by age group and in the overall propensity to migrate among households with children. With respect to the latter aim, our framework shares a common, discrete-choice framework with other, recent attempts to recover climate preferences, allowing us to explore the consequences of a number of key assumptions in a systematic manner. Consistent with the existing literature, we find relatively robust estimates of the impact of the frequency of extreme heat days on household location decisions. The impacts of other, common measures of climate, including the frequency of extreme cold days, average summer and winter temperatures, annual precipitation, humidity and frequency of sunshine, are not identified with precision. |
| Keywords: | climate amenities, discrete choice, robustness testing |
| JEL: | Q51 Q54 R23 |
| Date: | 2019–10 |
| URL: | http://d.repec.org/n?u=RePEc:mns:wpaper:wp201904&r=all |
| By: | Yuta Inoue (Graduate School of Economics, Waseda University); Koji Shirai (School of Economics, Kwansei Gakuin University) |
| Abstract: | This paper develops revealed preference tests for choice models under limited consideration, allowing a partially observed data set. Leading theories in the literature such as the limited attention model, the rationalization model, the categorize-then-choose model, and the rational shortlisting models are covered. Given a tool for testing limited consideration models, we analyze the empirical aspects of them. Our revealed preference tests are applied to randomly generated data sets to compare the strength of observable restrictions across various models. In addition, we carried out an experiment to compare models in terms of Selten’s index, which is a measure for plausibility of a model in explaining a given data set. As a result, remarkable differences are seen both in observable restrictions and Selten’s indices across models. |
| Keywords: | Revealed preference; Limited consideration; Limited attention; Rational shortlisting; Bronars’ test; Selten’s index |
| JEL: | C6 D1 D8 |
| Date: | 2018–03 |
| URL: | http://d.repec.org/n?u=RePEc:kgu:wpaper:176-2&r=all |
| By: | Amit Gandhi; Jean-François Houde |
| Abstract: | We study the estimation of substitution patterns within the discrete choice framework developed by Berry (1994) and Berry, Levinsohn, and Pakes (1995). Our objective, is to illustrate the consequences of using weak instruments in this non-linear GMM context, and propose a new class of instruments that can be used to estimate a large family of models with aggregate data. We argue that relevant instruments should reflect the (exogenous) degree of differentiation of each product in a market (Differentiation IVs), and provide a series of examples to illustrate the performance of simple instrument functions. |
| JEL: | C35 C36 L13 |
| Date: | 2019–10 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:26375&r=all |
| By: | M. Bockarjova; W.J.W. Botzen; Mark J. Koetse |
| Abstract: | There is an increased interest in applying nature-based solutions for addressing various urban challenges, such as those related to air pollution, climate change, and (mental) health. It is clear that nature can bring various benefits to city inhabitants, but the economic value of nature is not always well recognized. In this study we present a meta-analysis of a rapidly expanding literature that applied stated preference valuation methods to value green and blue urban nature in a variety of contexts. We estimate value transfer functions based on primary studies that elicited nature values from in total more than 41,000 respondents worldwide. We obtain insights into the main determinants of values of urban nature, in terms of study and methodological characteristics, types of nature, and ecosystem services. Main findings are that the per hectare value of nature is negatively related to the size of the nature area, and positively related to income and population density. Parks are the most highly valued types of urban nature, and aesthetics and cultural heritage services are the most highly valued ecosystem services it provides. Moreover, certain methodological choices in eliciting nature values appear to affect the final valuation results, such as the payment vehicle in stated preference surveys, and to some degree the valuation method. We present and illustrate the use of benefit transfer functions, which can be used for estimating the value of specific nature types and ecosystem services in a variety of urban settings. |
| Keywords: | benefit transfer, stated preferences, ecosystem services, meta-analysis, naturebased solution, urban nature |
| Date: | 2018 |
| URL: | http://d.repec.org/n?u=RePEc:use:tkiwps:1808&r=all |