|
on Discrete Choice Models |
| By: | James Holehouse; Jos\'e Moran |
| Abstract: | We provide a generic method to find full dynamical solutions to binary decision models with interactions. In these models, agents follow a stochastic evolution where they must choose between two possible choices by taking into account the choices of their peers. We illustrate our method by solving Kirman and F\"ollmer's ant recruitment model for any number $N$ of agents and for any choice of parameters, recovering past results found in the limit $N\to \infty$. We then solve extensions of the ant recruitment model for increasing asymmetry between the two choices. Finally, we provide an analytical time-dependent solution to the standard voter model and a semi-analytical solution to the vacillating voter model. |
| Date: | 2022–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2201.09573&r= |
| By: | Bo E. Honoré (Princeton University); Martin Weidner (University College London) |
| Abstract: | This paper builds on Bonhomme (2012) to develop a method to systematically construct moment conditions for dynamic panel data logit models with fixed effects. After introducing the moment conditions obtained in this way, we explore their implications for identification and estimation of the model parameters that are common to all individuals, and we find that those common model parameters are estimable at root-n rate for many more dynamic panel logit models than has been appreciated by the existing literature. In the case where the model contains one lagged variable, the moment conditions in Kitazawa (2013, 2016) are transformations of a subset of ours. A GMM estimator that is based on the moment conditions is shown to perform well in Monte Carlo simulations and in an empirical illustration to labor force participation. |
| Keywords: | dynamic panel data logit models, moment conditions |
| JEL: | C30 C33 |
| Date: | 2021–12 |
| URL: | http://d.repec.org/n?u=RePEc:pri:econom:2021-79&r= |
| By: | Emerson Melo (Indiana University, Bloomington) |
| Abstract: | This paper studies the Random Utility Model (RUM) in environments where the decision maker is imperfectly informed about the payoffs associated to each of the alternatives he faces. By embedding the RUM into an online decision problem, we make four contributions. First, we propose a gradient-based learning algorithm and show that a large class of RUMs are Hannan consistent (Hannan [1957]); that is, the average difference between the expected payoffs generated by a RUM and that of the best fixed policy in hindsight goes to zero as the number of periods increase. Second, we show that the class of Generalized Extreme Value (GEV) models can be implemented with our learning algorithm. Examples in the GEV class include the Nested Logit, Ordered, and Product Differentiation models among many others. Third, we show that our gradient-based algorithm is the dual, in a convex analysis sense, of the Follow the Regularized Leader (FTRL) algorithm, which is widely used in the Machine Learning literature. Finally, we discuss how our approach can incorporate recency bias and be used to implement prediction markets in general environments.javascript:void(0); |
| Keywords: | Random utility models, Multinomial Logit Model, Generalized Nested Logit models, GEV class, Online optimization, Online learning, Hannan consistency, no-regret learning |
| Date: | 2021–08 |
| URL: | http://d.repec.org/n?u=RePEc:inu:caeprp:2022003&r= |
| By: | Çam, Eren (Energiewirtschaftliches Institut an der Universitaet zu Koeln (EWI)); Hinkel, Niklas (Energiewirtschaftliches Institut an der Universitaet zu Koeln (EWI)); Schönfisch, Max (Energiewirtschaftliches Institut an der Universitaet zu Koeln (EWI)) |
| Abstract: | We present a methodology to estimate fixed cost parameters relevant to the decision to operate, mothball or retire an open-cycle gas turbine (OCGT) using a dynamic discrete choice model, based on fuel and electricity prices, as well as technical data and the operational status of OCGTs in the PJM market area. With operational and mothballed OCGTs, we find for both, age of the power plant and plant vintage statistically significant positive correlations with the fixed operation and maintenance (O&M) costs. We also show a statistically significant negative relationship between the installed capacity and the fixed O&M costs, confirming that an increase in scale results in lower specific costs. The estimated fixed O&M cost parameters for an operational OCGT vary from 15.3 USD/kW/yr for new, large, high-efficiency units, to 50.8 USD/kW/yr for older, small, low-efficiency units. Mothballing a plant reduces these costs by 75% to 95%, depending on plant vintage and size. Decommissioning an OCGT was found to be cash flow negative, which means that the associated cost exceeds any scrap value the equipment may have on secondary markets. Our estimated cost parameters depend on operational status, capacity, vintage, and age of a generation unit. This differentiation is valuable for a better understanding of costs in the context of competition policy. It would also allow for a more realistic parameterisation of power market models. Using the estimates and market data, we also compute the probabilities of operating, mothballing or retiring an OCGT. Sensitivity analyses regarding changes in prices of capacity, electricity, and natural gas reveal that the operating decisions for OCGTs are significantly affected by the profitability potential, most notably by electricity prices. |
| Keywords: | Dynamic discrete choice models; electricity markets; fixed cost estimation; maximum likelihood estimation; open-cycle gas turbine (OCGT) |
| JEL: | C61 D24 L94 |
| Date: | 2022–02–14 |
| URL: | http://d.repec.org/n?u=RePEc:ris:ewikln:2022_001&r= |
| By: | Anna Birgitte Milford (NIBIO - Norwegian Institute of Bioeconomy Research); Nina Trandem (NIBIO - Norwegian Institute of Bioeconomy Research); Armando José Garcia Pires |
| Abstract: | Due to an EU directive making integrated pest management (IPM) mandatory, European farmers are expected to reduce their use of chemical pesticides, which may potentially increase production costs and risk of harvest loss. Less pesticide use is appreciated by many consumers and may generate a higher willingness to pay (WTP). However, IPM is a wide concept and it is difficult for consumers to distinguish between products with high and low risk of pesticide residues. As a result, consumers might use other characteristics, such as country of origin, for the identification of safer products. In this study, we investigate if a higher WTP for Norwegian strawberries is associated with a belief that they contain less pesticide residues than imported berries. We use regression analysis to estimate to what extent the difference in WTP for Norwegian and imported strawberries is correlated with various perceptions about strawberries. The analyses reveal that the stronger the belief that Norwegian strawberries have less pesticide risk than imported ones, the higher the WTP for Norwegian strawberries. This means that if consumers believe domestic farmers use little pesticides, domestic products might be able to sell at considerably higher prices than imports. Hence, it may be economically beneficial for farmers to keep pesticide use at a minimum. Furthermore, we find that consumers have a higher WTP for strawberries produced with less use of pesticides, although not pesticide-free, indicating that IPM is appreciated. |
| Keywords: | Strawberries,Country of origin,Pesticides,Norway,Willingness to pay (WTP),Integrated pest management (IPM) |
| Date: | 2021 |
| URL: | http://d.repec.org/n?u=RePEc:hal:journl:hal-03527986&r= |
| By: | Olivier Jacques |
| Abstract: | While public opinion research has identified the drivers of preferences for tax progressivity, public spending and support for redistribution, the study of willingness to pay taxes remains underdeveloped. This paper uses the 2016 ISSP cross national survey on the Role of Government and the Risks that Matter survey (OECD 2018) to identify which groups of voters are more likely to be willing to pay higher taxes. It shows that ideology and income interact to predict willingness to pay. Among left-wing respondents, socio-economic status, measured by income and education, has a positive effect on willingness to pay additional taxes. Thus, the core constituencies of left-wing parties composed of socio-cultural professionals and of production and service workers have different tax policy preferences. Socio-cultural professionals have a higher socio-economic status and are significantly more willing to pay taxes than production and service workers, who share a lower socio-economic status. Si les recherches sur l'opinion publique ont permis d'identifier les moteurs des préférences en matière de progressivité de l'impôt, de dépenses publiques et de soutien à la redistribution, l'étude de la volonté de payer des impôts reste peu développée. Cet article utilise l'enquête transnationale 2016 de l'ISSP sur le rôle du gouvernement et les risques qui comptent (OCDE 2018) pour identifier les groupes d'électeurs les plus susceptibles d'être disposés à payer des impôts plus élevés. Elle montre que l'idéologie et le revenu interagissent pour prédire la volonté de payer. Parmi les répondants de gauche, le statut socio-économique, mesuré par le revenu et l'éducation, a un effet positif sur la volonté de payer des impôts supplémentaires. Ainsi, les principaux électeurs des partis de gauche, composés de professionnels socioculturels et de travailleurs de la production et des services, ont des préférences différentes en matière de politique fiscale. Les professionnels socioculturels ont un statut socio-économique plus élevé et sont significativement plus disposés à payer des impôts que les travailleurs de la production et des services, qui ont un statut socio-économique plus faible. |
| Keywords: | taxation,occupations,ideology,education,Europe,income, fiscalité,professions,idéologie,revenu,éducation,Europe |
| JEL: | C83 D72 H20 H30 H31 |
| Date: | 2021–09–21 |
| URL: | http://d.repec.org/n?u=RePEc:cir:cirwor:2021s-37&r= |
| By: | Ayden Higgins; Koen Jochmans |
| Abstract: | The maximum-likelihood estimator of nonlinear panel data models with fixed effects is consistent but asymptotically-biased under rectangular-array asymptotics. The literature has thus far concentrated its effort on devising methods to correct the maximum-likelihood estimator for its bias as a means to salvage standard inferential procedures. Instead, we show that the parametric bootstrap replicates the distribution of the (uncorrected) maximum-likelihood estimator in large samples. This justifies the use of confidence sets constructed via standard bootstrap percentile methods. No adjustment for the presence of bias needs to be made. |
| Date: | 2022–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2201.11156&r= |
| By: | Stephan Martin |
| Abstract: | Nonparametric random coefficient (RC)-density estimation has mostly been considered in the marginal density case under strict independence of RCs and covariates. This paper deals with the estimation of RC-densities conditional on a (large-dimensional) set of control variables using machine learning techniques. The conditional RC-density allows to disentangle observable from unobservable heterogeneity in partial effects of continuous treatments adding to a growing literature on heterogeneous effect estimation using machine learning. %It is also informative of the conditional potential outcome distribution. This paper proposes a two-stage sieve estimation procedure. First a closed-form sieve approximation of the conditional RC density is derived where each sieve coefficient can be expressed as conditional expectation function varying with controls. Second, sieve coefficients are estimated with generic machine learning procedures and under appropriate sample splitting rules. The $L_2$-convergence rate of the conditional RC-density estimator is derived. The rate is slower by a factor then typical rates of mean regression machine learning estimators which is due to the ill-posedness of the RC density estimation problem. The performance and applicability of the estimator is illustrated using random forest algorithms over a range of Monte Carlo simulations and with real data from the SOEP-IS. Here behavioral heterogeneity in an economic experiment on portfolio choice is studied. The method reveals two types of behavior in the population, one type complying with economic theory and one not. The assignment to types appears largely based on unobservables not available in the data. |
| Date: | 2022–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2201.08366&r= |
| By: | Nisvan Erkal; Lijun Pan |
| Abstract: | We consider mergers between multi-product firms in a market with monopolistically competitive fringe of single-product firms. Aggregate product variety is determined by product variety choices of multi-product firms and entry/exit decisions of single-product firms. Mergers can generate marginal cost synergies (affecting marginal cost of quantity) or fixed cost synergies (affecting marginal cost of variety). We show that with marginal cost synergies, consumer welfare decreases whenever aggregate variety increases following a merger. However, with fixed cost synergies, an increase in aggregate variety can indicate that the merger is beneficial. Our results also show high synergies do not necessarily improve consumer welfare. |
| Date: | 2022–02 |
| URL: | http://d.repec.org/n?u=RePEc:dpr:wpaper:1162&r= |
| By: | Morteza Taiebat; Elham Amini; Ming Xu |
| Abstract: | Ride-hailing is rapidly changing urban and personal transportation. Ride sharing or pooling is important to mitigate negative externalities of ride-hailing such as increased congestion and environmental impacts. However, there lacks empirical evidence on what affect trip-level sharing behavior in ride-hailing. Using a novel dataset from all ride-hailing trips in Chicago in 2019, we show that the willingness of riders to request a shared ride has monotonically decreased from 27.0% to 12.8% throughout the year, while the trip volume and mileage have remained statistically unchanged. We find that the decline in sharing preference is due to an increased per-mile costs of shared trips and shifting shorter trips to solo. Using ensemble machine learning models, we find that the travel impedance variables (trip cost, distance, and duration) collectively contribute to 95% and 91% of the predictive power in determining whether a trip is requested to share and whether it is successfully shared, respectively. Spatial and temporal attributes, sociodemographic, built environment, and transit supply variables do not entail predictive power at the trip level in presence of these travel impedance variables. This implies that pricing signals are most effective to encourage riders to share their rides. Our findings shed light on sharing behavior in ride-hailing trips and can help devise strategies that increase shared ride-hailing, especially as the demand recovers from pandemic. |
| Date: | 2022–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2201.12696&r= |