|
on Discrete Choice Models |
| By: | González Dávila, Osiel; Koundouri, Phoebe; Pantelidis, Theologos; Papandreou, Andreas |
| Abstract: | In this paper we develop a full-preference ranking Choice Experiment (CE) designed to investigate how respondents evaluate a set of proposed improvements towards sustainable river basin management, as per the prescriptions of the European Union-Water Framework Directive (2000). The CE is applied in the Asopos River Basin (ARB) in Greece. Our interest is to test whether residency in the river basin, or otherwise, affects the preferences of the relevant agents. We first estimate a rank-ordered logistic regression based on a full set of choices in order to calculate the willingness to pay (WTP) of respondents for each one of the three attributes considered in the CE (i.e., environmental conditions, impact on the local economy and changes in the potential uses of water). The model is initially estimated for the full sample and then re-estimated twice for two sub-samples: the first one only includes the residents of Athens and the second only includes the residents of Asopos. Afterwards, we examine the effect of various demographic and socio-economic factors (such as income, gender, age, employment and education) on the estimates of our model in order to reveal any differences among respondents with different characteristics, mainly focusing on whether they reside or have personal experience of the RB under valuation. Thus, our analysis simultaneously provides a robustness check on previous findings in the literature and additional information about how various demographic and socio-economic characteristics affect the evaluation of the selected attributes. |
| Keywords: | choice experiment; full-preference ranking; Asopos River Basin; water quality and quantity; Water Framework Directive; willingness to pay |
| JEL: | Q25 Q51 Q53 |
| Date: | 2017–01–01 |
| URL: | http://d.repec.org/n?u=RePEc:ehl:lserod:68893&r=dcm |
| By: | Lea Skræp Svenningsen (Department of Food and Resource Economics, University of Copenhagen) |
| Abstract: | This study examines whether people have distributional preferences for the impacts of climate policy when making donations towards such policies. In an online choice experiment, using a real donation mechanism, a representative sample of 95 members of the Danish public are provided 27€ and asked to make 16 donation choices among different climate policy options. The climate policies are described in terms of two main outcome variables, including future effects on income in 2100 and present co-benefits from mitigation action. Both outcomes are described for three specific regions of the world, Western Europe, Southeast Asia and Sub-Saharan Africa. For each participant, one policy choice was drawn at random to be realised and the total amount donated by participants was used to purchase and withdraw CO2 quotas and credits in the European Emission Trading Scheme and as a donation to the UN Adaptation Fund. A random parameter logit model shows that distributional concerns matter for people when they donate to climate policy and that elements of both inequity aversion and general altruism influence the choice of climate policy. The results underscore the importance of considering preferences for distributional outcomes when designing climate policy. |
| Keywords: | choice experiment, climate change, inequity aversion, altruism, random parameters logit, intergenerational, distributional social preferences |
| JEL: | D30 D91 Q51 Q54 Q58 |
| Date: | 2017–10 |
| URL: | http://d.repec.org/n?u=RePEc:foi:wpaper:2017_11&r=dcm |
| By: | Vojnovic, Milan; Yun, Seyoung |
| Abstract: | We consider the maximum likelihood parameter estimation problem for a generalized Thurstone choice model, where choices are from comparison sets of two or more items. We provide tight characterizations of the mean square error, as well as necessary and sufficient conditions for correct classification when each item belongs to one of two classes. These results provide insights into how the estimation accuracy depends on the choice of a generalized Thurstone choice model and the structure of comparison sets. We find that for a priori unbiased structures of comparisons, e.g., when comparison sets are drawn independently and uniformly at random, the number of observations needed to achieve a prescribed estimation accuracy depends on the choice of a generalized Thurstone choice model. For a broad set of generalized Thurstone choice models, which includes all popular instances used in practice, the estimation error is shown to be largely insensitive to the cardinality of comparison sets. On the other hand, we found that there exist generalized Thurstone choice models for which the estimation error decreases much faster with the cardinality of comparison sets. |
| JEL: | C1 |
| Date: | 2016–06–20 |
| URL: | http://d.repec.org/n?u=RePEc:ehl:lserod:85703&r=dcm |
| By: | de Bresser, Jochem (Tilburg University, Center For Economic Research); van Soest, Arthur (Tilburg University, Center For Economic Research) |
| Abstract: | This paper evaluates the predictive validity of stated intentions for actual behaviour. In the context of the 2017 Dutch parliamentary election, we compare how well polls based on probabilistic and deterministic questions line up with subsequent votes. Our empirical strategy is built around a randomised experiment in a representative panel. Respondents were either simply asked which party they will vote for, or were asked to allocate probabilities of voting for each party. The results show that for the large majority of the respondents, probabilities predict individual behaviour better than deterministic statements. There is, however, substantial heterogeneity in the predictive power of the subjective probabilities. We find evidence that they work better for those with higher probability numeracy, even though probability numeracy was measured eight years earlier. |
| Keywords: | subjective probabilities; predictive validity; probabilistic polling; elections |
| JEL: | D84 C81 C25 |
| Date: | 2017 |
| URL: | http://d.repec.org/n?u=RePEc:tiu:tiucen:67bd2341-45c7-4e60-99e5-ff32b1be1668&r=dcm |
| By: | Bonhomme, Stéphane (University of Chicago); Lamadon, Thibaut (University of Chicago); Manresa, Elena (Massachusetts Institute of Technology and The Sloan School of Mangement) |
| Abstract: | We study panel data estimators based on a discretization of unobserved heterogeneity when individual heterogeneity is not necessarily discrete in the population. We focus on two-step grouped-fixed effects estimators, where individuals are classified into groups in a first step using kmeans clustering, and the model is estimated in a second step allowing for group-specific heterogeneity. We analyze the asymptotic properties of these discrete estimators as the number of groups grows with the sample size, and we show that bias reduction techniques can improve their performance. In addition to reducing the number of parameters, grouped fixed-effects methods provide effective regularization. When allowing for the presence of time-varying unobserved heterogeneity, we show they enjoy fast rates of convergence depending of the underlying dimension of heterogeneity. Finally, we document the finite sample properties of two-step grouped fixed-effects estimators in two applications: a structural dynamic discrete choice model of migration, and a model of wages with worker and firm heterogeneity. |
| Keywords: | dimension reduction; panel data; structural models; kmeans clustering |
| JEL: | C23 C38 |
| Date: | 2017–11–21 |
| URL: | http://d.repec.org/n?u=RePEc:hhs:ifauwp:2017_021&r=dcm |