
on Discrete Choice Models 
By:  Riccardo Di Francesco (DEF, University of Rome "Tor Vergata") 
Abstract:  Empirical studies in various social sciences often involve categorical outcomes with inherent ordering, such as selfevaluations of subjective wellbeing and selfassessments in health domains. While ordered choice models, such as the ordered logit and ordered probit, are popular tools for analyzing these outcomes, they may impose restrictive parametric and distributional assumptions. This paper introduces a novel estimator, the ordered correlation forest, that can naturally handle nonlinearities in the data and does not assume a specific error term distribution. The proposed estimator modifies a standard random forest splitting criterion to build a collection of forests, each estimating the conditional probability of a single class. Under an “honesty” condition, predictions are consistent and asymptotically normal. The weights induced by each forest are used to obtain standard errors for the predicted probabilities and the covariates’ marginal effects. Evidence from synthetic data shows that the proposed estimator features a superior prediction performance than alternative forestbased estimators and demonstrates its ability to construct valid confidence intervals for the covariates’ marginal effects. 
Keywords:  Ordered nonnumeric outcomes, choice probabilities, machine learning 
JEL:  C14 C25 C55 
Date:  2024–05–06 
URL:  http://d.repec.org/n?u=RePEc:rtv:ceisrp:577&r= 
By:  Elena Panova (TSER  Toulouse School of Economics  UT Capitole  Université Toulouse Capitole  UT  Université de Toulouse  EHESS  École des hautes études en sciences sociales  CNRS  Centre National de la Recherche Scientifique  INRAE  Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement) 
Abstract:  We consider the problem of sharing the cost of a fixed treenetwork among users with differentiated willingness to pay for the good supplied through the network. We find that the associated valuesharing problem is convex, hence, the core is large and we axiomatize a new, computationally simple core selection based on the idea of proportionality. 
Keywords:  Sharing network cost, Core, Proportional allocation 
Date:  2023–11 
URL:  http://d.repec.org/n?u=RePEc:hal:journl:hal04556220&r= 
By:  Ayden Higgins (University of Oxford); Koen Jochmans (TSER  Toulouse School of Economics  UT Capitole  Université Toulouse Capitole  UT  Université de Toulouse  EHESS  École des hautes études en sciences sociales  CNRS  Centre National de la Recherche Scientifique  INRAE  Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement) 
Abstract:  The maximumlikelihood estimator of nonlinear panel data models with fixed effects is asymptotically biased under rectangulararray asymptotics. The literature has devoted substantial effort to devising methods that correct for this bias as a means to salvage standard inferential procedures. The chief purpose of this paper is to show that the (recursive, parametric) bootstrap replicates the asymptotic distribution of the (uncorrected) maximumlikelihood estimator and of the likelihoodratio statistic. This justifies the use of confidence sets and decision rules for hypothesis testing constructed via conventional bootstrap methods. No modification for the presence of bias needs to be made. 
Keywords:  Bootstrap, Fixed effects, Incidentalparameter problem, Inference, Panel data 
Date:  2024–03 
URL:  http://d.repec.org/n?u=RePEc:hal:journl:hal04557288&r= 
By:  Sudhir A. Shah (Department of Economics, Delhi School of Economics) 
Abstract:  We propose an asset’s moneymetric value as the appropriate representation of its subjective value to an investor. This value is expressed in monetary terms and is invariant across equivalent utility representations of the investor’s preference. The ordering of moneymetric values across assets matches the investor’s preference ordering over the assets.The moneymetric value of a risky asset is inversely related to the investor’s risk aversion, while the moneymetric value of a riskfree asset is uniform across preferences with comparable riskaversion. Finally, an asset’s arbitragefree market price is the sum of its moneymetric value and the investor’s willingnesstopay for fully derisking the asset. JEL Code: G11, G12 
Keywords:  moneymetric asset valuation, arbitragefree prices, risk aversion 
Date:  2024–04 
URL:  http://d.repec.org/n?u=RePEc:cde:cdewps:347&r= 
By:  Xin Liu 
Abstract:  I propose a quantilebased nonadditive fixed effects panel model to study heterogeneous causal effects. Similar to standard fixed effects (FE) model, my model allows arbitrary dependence between regressors and unobserved heterogeneity, but it generalizes the additive separability of standard FE to allow the unobserved heterogeneity to enter nonseparably. Similar to structural quantile models, my model's random coefficient vector depends on an unobserved, scalar ''rank'' variable, in which outcomes (excluding an additive noise term) are monotonic at a particular value of the regressor vector, which is much weaker than the conventional monotonicity assumption that must hold at all possible values. This rank is assumed to be stable over time, which is often more economically plausible than the panel quantile studies that assume individual rank is iid over time. It uncovers the heterogeneous causal effects as functions of the rank variable. I provide identification and estimation results, establishing uniform consistency and uniform asymptotic normality of the heterogeneous causal effect function estimator. Simulations show reasonable finitesample performance and show my model complements fixed effects quantile regression. Finally, I illustrate the proposed methods by examining the causal effect of a country's oil wealth on its military defense spending. 
Date:  2024–05 
URL:  http://d.repec.org/n?u=RePEc:arx:papers:2405.03826&r= 