|
on Discrete Choice Models |
| By: | Easton K. Huch; Michael P. Keane |
| Abstract: | Discrete choice models are fundamental tools in management science, economics, and marketing for understanding and predicting decision-making. Logit-based models are dominant in applied work, largely due to their convenient closed-form expressions for choice probabilities. However, these models entail restrictive assumptions on the stochastic utility component, constraining our ability to capture realistic and theoretically grounded choice behavior—most notably, substitution patterns. In this work, we propose an amortized inference approach using a neural network emulator to approximate choice probabilities for general error distributions, including those with correlated errors. Our proposal includes a specialized neural network architecture and accompanying training procedures designed to respect the invariance properties of discrete choice models. We provide group-theoretic foundations for the architecture, including a proof of universal approximation given a minimal set of invariant features. Once trained, the emulator enables rapid likelihood evaluation and gradient computation. We use Sobolev training, augmenting the likelihood loss with a gradient-matching penalty so that the emulator learns both choice probabilities and their derivatives. We show that emulator-based maximum likelihood estimators are consistent and asymptotically normal under mild approximation conditions, and we provide sandwich standard errors that remain valid even with imperfect likelihood approximation. Simulations show significant gains over the GHK simulator in accuracy and speed. |
| JEL: | C10 C13 C15 C25 C35 C45 |
| Date: | 2026–04 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:35037 |
| By: | Gkargkavouzi, Anastasia; Halkos, George |
| Abstract: | Non-market environmental valuation studies have incorporated and empirically examined a structured set of cognitive determinants underlying individual preferences, yet the role of affective responses remains theoretically underdeveloped. Literature suggests that incidental emotions, or mood states unrelated to the ecosystem being valued, have no significant effect on stated preferences, a null result further corroborated by ambient weather as an additional incidental trigger. Drawing on the integral/incidental distinction from the decision-making literature, we argue that this null result constitutes a boundary condition and not a general decision on the role of affect in valuation. We propose an Affective Framework, organizing eco-emotions by motivational orientation (approach versus avoidance) and semantic origin (integral versus incidental). Approach-oriented positive eco-emotions, including awe, hope, connectedness to nature, and perceived restorativeness, are predicted to amplify stated preferences. Approach-oriented negative eco-emotions, such as eco-worry, moral guilt, solastalgia, and anticipated regret, activate environmental concern and elevate willingness to pay. Avoidance-oriented eco-emotions, notably clinical eco-anxiety, despair, and eco-paralysis, suppress stated preferences by reducing perceived self-efficacy. Three mechanisms ground these predicted effects: the risk-as-feelings hypothesis, the affect heuristic, and feelings as information theory. The proposed framework offers a theoretically coherent explanation for a previously unexplained method effect in stated preference research and informs future empirical investigation. |
| Keywords: | Eco-emotions; non-market valuation; stated preferences; willingness to pay; integral affect; affect heuristic; eco-anxiety. |
| JEL: | A12 A14 D12 I20 I30 Q00 Q01 Q50 Q51 |
| Date: | 2026–04–07 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:128609 |
| By: | Yoshitsugu Kitazawa (Faculty of Economics, Kyushu Sangyo University) |
| Abstract: | This paper proposes linear estimation methods for dynamic fixed effects logit models only with time effects (i.e., those only with time dummies and only with time trends). The linear estimators point-identify transformations of parameters of interest for the models if five or more time periods are provided and then point-identify the parameters of interest. What it boils down to is that root-N consistent estimations are attainable for these models. Monte Carlo results corroborate this conclusion. |
| Keywords: | Keywords: dynamic panel logit models; fixed effects; time dummies; time trends; point-identification; root-N consistent estimators; Monte Carlo experiments |
| JEL: | C23 C25 C26 |
| Date: | 2026–03 |
| URL: | https://d.repec.org/n?u=RePEc:kyu:dpaper:87 |
| By: | Wayne Yuan Gao; Yi Niu |
| Abstract: | This paper establishes (set) identification results in a dynamic dyadic network formation model with time-varying observed covariates, lagged local network statistics, and unobserved heterogeneity in the form of fixed effects. Our framework accommodates observed-covariate homophily, transitivity through common friends, second-order or indirect-friend effects, and more general local subgraph statistics within a single dynamic index model. The analysis combines two complementary ways of handling fixed effects: inequalities that integrate out time-invariant dyad heterogeneity by treating each dyad as a short panel, and signed-subgraph comparisons that difference out fixed effects algebraically through intertemporal variation within each dyad. We show that the semiparametric identifying restrictions can be sharpened using either or both of the following assumptions: (i) error distribution is serially independent with a known distribution, (ii) pairwise fixed effect takes the form of additive individual fixed effects. Combining (i) and (ii) under i.i.d. logit shocks, we obtain an exact conditional logit representation and provide sufficient conditions for point identification. |
| Date: | 2026–04 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2604.07488 |
| By: | Federico Echenique; Gerelt Tserenjigmid |
| Abstract: | McGranaghan, Nielsen, O'Donoghue, Somerville, and Sprenger [2024] argue that standard paired choice tests for the common ratio effect are structurally biased when choice is stochastic, proposing valuation tests as a robust alternative. Using valuation tests, they find no systematic evidence for the common ratio effect, seemingly overturning much of the extant literature. We evaluate this conclusion in light of stochastic choice theory. We demonstrate that valuation tests are inherently biased and lack predictive power under standard expected utility assumptions. In contrast, we advocate for a ``strong'' paired choice test, proving it remains robustly unbiased across standard models of stochastic choice. Applying this strong test to existing experimental data, we find that the common ratio effect remains highly prevalent. |
| Date: | 2026–04 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2604.06050 |
| By: | Zizhong Yan; Zhengyu Zhang; Mingli Chen; Jingrong Li; Iv\'an Fern\'andez-Val |
| Abstract: | We develop likelihood-based bias reduction for nonlinear panel models with additive individual and time effects. In two-way panels, integrated-likelihood corrections are attractive but challenging because the required integration is high dimensional and standard Laplace approximations may fail when the parameter dimension grows with the sample size. We propose a target-centered full-exponential Laplace--cumulant expansion that exploits the sparse higher-order derivative structure implied by additive effects, delivering a tractable approximation with a negligible remainder under large-$N, T$ asymptotics. The expansion motivates robust priors that yield bias reduction for both common parameters and fixed effects. We provide implementations for binary, ordered, and multinomial response models with two-way effects. For average partial effects, we show that the remaining first-order bias has a simple variance form and can be removed by a closed-form adjustment. Monte Carlo experiments and an empirical illustration show substantial bias reduction with accurate inference. |
| Date: | 2026–04 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2604.03663 |