Multiplicity and Uniqueness of Equilibria in Continuous-Time Dynamic Discrete Games

Jason R. Blevins; Youngjae Jeong

Home/Archive/arXiv

arXiv · 2610.33660

Multiplicity and Uniqueness of Equilibria in Continuous-Time Dynamic Discrete Games

Jason R. Blevins·Youngjae Jeong

View original source ↗Read source document ↗Export metadata ↓

Abstract

We consider multiplicity and uniqueness of equilibria in continuous-time dynamic discrete games where players move sequentially according to independent Poisson processes. With multiple equilibria, the structural model is incomplete: the reduced form and counterfactual predictions depend on how equilibria are selected. We provide closed-form sufficient conditions for uniqueness of Markov perfect equilibrium in this class of games. The conditions are semiparametric and can be verified from model primitives. To measure the coverage of the conditions and characterize multiplicity more broadly, we carry out a large-scale numerical search for equilibria of a dynamic duopoly model of entry and exit. Although uniqueness is the norm in our broad search, we find that multiplicity concentrates in economically relevant regions: where the market cannot profitably sustain both firms, where firms are very patient, and at intermediate decision frequencies that balance strategic interaction and commitment. When multiplicity is present, we typically find two stable asymmetric equilibria and one unstable symmetric equilibrium. Monte Carlo and counterfactual simulations show this structure matters for empirical work. A full-solution estimator that assumes uniqueness can converge to the unstable equilibrium, even when the data were generated by a stable one, while a two-step estimator recovers the correct equilibrium.

Explore related subjects

econ.EM

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Jason R. Blevins, Youngjae Jeong. 2026-10-24. Multiplicity and Uniqueness of Equilibria in Continuous-Time Dynamic Discrete Games. https://arxiv.org/abs/2610.33660

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Instrumented Difference-in-Differences with Heterogeneous Treatment Effects

Many studies exploit variation in the timing of policy adoption across units as an instrument for treatment. This paper formalizes the underlying identification strategy as a staggered instrumented difference-in-differences (DID-IV). In this design, a Wald-DID estimand, which scales the DID estimand of the outcome by the DID estimand of the treatment, captures the cohort specific local average treatment effect on the treated (CLATT). We propose a credible estimation method in this design that is robust to treatment effect heterogeneity. We also provide simultaneous inference procedures based on the multiplier bootstrap. We illustrate the empirical relevance of our findings, estimating returns to schooling in the United Kingdom. In this application, the two-way fixed effects instrumental variable regression, the conventional approach to implement DID-IV designs, yields a negative estimate. By contrast, our estimation method indicates a substantial gain from schooling.

econ.EM↗

arXiv2026

Bias-robust causal inference for panel data

We develop a bias-robust framework for causal inference in panel data models with interactive fixed effects. Conventional imputation-based estimators of average treatment effects on the treated do not explicitly account for counterfactual approximation error, potentially leading to misleading inference. Building on bias-aware minimax methods, we construct an estimator that corrects imputed counterfactuals using weighted untreated residuals and delivers confidence intervals with an explicit allowance for the remaining approximation bias. The resulting framework separates protection against approximation bias from the efficiency gains obtained through optimal correction. In simulations, the correction reduces confidence interval length by approximately 13\% relative to bias-aware inference without correction, while preserving empirical coverage. An application to Election Day Registration demonstrates how the correction strengthens the robustness of substantive conclusions to counterfactual error. The proposed approach provides a transparent sensitivity analysis for causal effects when the accuracy of counterfactual imputation cannot be established from observed data alone.

econ.EM↗

arXiv2026

Cordon Tolls and Urban Traffic Volumes: Evidence from NYC's 2025 Congestion Relief Zone

On January 5, 2025, New York City became the first U.S. city to operate a permanent cordon-based congestion toll, charging vehicles entering Manhattan's Central Business District (the Congestion Relief Zone, or CRZ). This study estimates the short-run causal effect of the toll on hourly traffic volumes using a two-way fixed-effects difference in-differences (TWFE-DiD) strategy that compares treated CRZ street segments to untreated Manhattan segments north of 60th Street. The empirical analysis exploits hourly entry counts from the MTA's toll-meter system (4.86 million ten-minute-block records) as the primary descriptive panel and high-frequency NYC DOT Automated Traffic Recorder (ATR) data as the within-segment identification panel. The headline TWFE-DiD point estimate indicates a 40 to 45 percent reduction in log hourly volume at treated CRZ locations, with the effect direction consistent across nine pre-registered alternative specifications and concentrated in peak hours. East River bridges in the balanced panel exhibit a statistically significant 25 percent post-period increase in volume, consistent with route substitution.

econ.EM↗