arXiv subjects

Myung Hwan Seo

Publications and source records attributed to Myung Hwan Seo.

At least 19 recordsLinked to original sources

arXiv2026

SLIM: Stochastic Learning and Inference in Overidentified Models

We propose SLIM (Stochastic Learning and Inference in overidentified Models), a scalable stochastic approximation framework for nonlinear GMM. Independent mini-batches of moments and derivatives yield unbiased update directions with martingale difference noise. Under suitable regularity conditions, SLIM yields consistent and asymptotically normal estimators without a consistent initial estimator or a globally convex GMM criterion. Our theory covers fixed-sample and random-sampling asymptotics. An optional second-order refinement achieves full-sample GMM efficiency. Random-scaling and plug-in inference account for sampling and computational uncertainty, while debiased $J$-tests permit specification testing with SLIM. We extend the framework to clustered data with unequal cluster sizes, preserving the form of the inference procedures. Monte Carlo experiments for a nonlinear demand system with 576 moments and 380 parameters demonstrate computational gains and scalability to one million observations. A large-scale LinkedIn application with 4.8 million college graduates illustrates clustered estimation and inference for first employment destinations.

econ.EM↗

arXiv2026

A Stochastic Nested Fixed Point Algorithm for Large-Scale BLP Estimation

We develop a stochastic nested fixed point (SNFP) estimator for random coefficients logit demand models that updates model parameters using stochastic gradients and performs demand inversion one market at a time. Relative to the conventional nested fixed point (NFP) estimator, SNFP substantially reduces memory requirements and computational cost, making estimation feasible in very large datasets. We establish the large-$T$ (number of markets) asymptotic properties of the estimator under regularity conditions. We also characterize the effect of sharing one block of simulation draws across markets and show how to correct for it. Monte Carlo simulations show that the SNFP estimator achieves statistical accuracy comparable to the NFP estimator, and in our benchmark a single online pass estimates a model with 100 million markets in about 5.5 hours. An empirical application using scanner data further demonstrates the practical advantages of SNFP for large-scale demand estimation.

econ.EM↗

arXiv2026

SAUSS: Stochastic Approximation with Unbiased Simulated Scores for Limited Dependent Variable Models

Multinomial choice models allow flexible substitution patterns but become computationally demanding with many alternatives or observations. With a fixed per-observation simulation budget, simulated maximum likelihood introduces simulation bias, while each optimization step requires a full-sample likelihood evaluation. We propose Stochastic Approximation with Unbiased Simulated Scores (SAUSS), an averaged stochastic approximation based on conditionally unbiased mini-batch score estimates. Each iteration uses a fixed mini-batch regardless of sample size. For multinomial probit, accept-reject sampling provides exact conditional draws and unbiased score estimates for any fixed number of accepted draws. Under local conditions, asymptotic theory for the averaged estimator and the partial-sum process of the SAUSS iterates incorporates mini-batch and simulation variability and supports random-scaling and plug-in inference. In simulations and an application, SAUSS gives comparable results in less than 1% of the computation time of simulated maximum likelihood. SAUSS extends to limited dependent variable models with conditional-expectation score representations and exact conditional sampling.

stat.ME↗

arXiv2026

What Impulse Response Do Instrumental Variables Identify?

The local projection-instrumental variable (LP-IV) literature has been largely silent on cases in which impulse responses are set-identified, arising when the shock of interest is composite and instruments are correlated with multiple components. We demonstrate that LP-IV estimands constructed using one instrument at a time identify affine combinations of impulse responses to structural shock components with instrument-specific and potentially negative weights, challenging standard causal interpretation. The two-stage least squares compounds the identification problem. However, we show that individual LP-IV estimands characterize the identified set when sign restrictions on the correlations between instruments and structural shock components are imposed. Under weak stationarity, these identified sets are sharp and cannot be further narrowed in key cases. Two empirical examples--decomposing the U.S. government spending multiplier and disentangling pure monetary shocks from central bank information shocks--illustrate the usefulness of our approach.

econ.EM↗

arXiv2025

Bootstraps for Dynamic Panel Threshold Models

This paper develops valid bootstrap inference methods for the dynamic short panel threshold regression. We show that the standard nonparametric bootstrap is inconsistent for the first-differenced generalized method of moments (GMM) estimator. The inconsistency arises from an $n^{1/4}$-consistent non-normal asymptotic distribution of the threshold estimator when the true parameter lies in the continuity region of the parameter space, which stems from the rank deficiency of the approximate Jacobian of the sample moment conditions on the continuity region. To address this, we propose a grid bootstrap to construct confidence intervals for the threshold and a residual bootstrap to construct confidence intervals for the coefficients. They are shown to be valid regardless of the model's continuity. Moreover, we establish a uniform validity for the grid bootstrap. A set of Monte Carlo experiments compares the proposed bootstraps with the standard nonparametric bootstrap. An empirical application to a firm investment model illustrates our methods.

econ.EM↗

arXiv2025

Optimal break tests for large linear time series models

We develop a class of optimal tests for a structural break occurring at an unknown date in infinite and growing-order time series regression models, such as AR($\infty$), linear regression with increasingly many covariates, and nonparametric regression. Under an auxiliary i.i.d. Gaussian error assumption, we derive an average power optimal test, establishing a growing-dimensional analog of the exponential tests of Andrews and Ploberger (1994) to handle identification failure under the null hypothesis of no break. Relaxing the i.i.d. Gaussian assumption to a more general dependence structure, we establish a functional central limit theorem for the underlying stochastic processes, which features an extra high-order serial dependence term due to the growing dimension. We robustify our test both against this term and finite sample bias and illustrate its excellent performance and practical relevance in a Monte Carlo study and a real data empirical example.

econ.EM↗

arXiv2024

Inference for parameters identified by conditional moment restrictions using a generalized Bierens maximum statistic

Many economic panel and dynamic models, such as rational behavior and Euler equations, imply that the parameters of interest are identified by conditional moment restrictions. We introduce a novel inference method without any prior information about which conditioning instruments are weak or irrelevant. Building on Bierens (1990), we propose penalized maximum statistics and combine bootstrap inference with model selection. Our method optimizes asymptotic power by solving a data-dependent max-min problem for tuning parameter selection. Extensive Monte Carlo experiments, based on an empirical example, demonstrate the extent to which our inference procedure is superior to those available in the literature.

econ.EM↗

arXiv2024

Regression Discontinuity Design with Potentially Many Covariates

This paper studies the case of possibly high-dimensional covariates in the regression discontinuity design (RDD) analysis. In particular, we propose estimation and inference methods for the RDD models with covariate selection which perform stably regardless of the number of covariates. The proposed methods combine the local approach using kernel weights with $\ell_{1}$-penalization to handle high-dimensional covariates. We provide theoretical and numerical results which illustrate the usefulness of the proposed methods. Theoretically, we present risk and coverage properties for our point estimation and inference methods, respectively. Under certain special case, the proposed estimator becomes more efficient than the conventional covariate adjusted estimator at the cost of an additional sparsity condition. Numerically, our simulation experiments and empirical example show the robust behaviors of the proposed methods to the number of covariates in terms of bias and variance for point estimation and coverage probability and interval length for inference.

econ.EM↗

arXiv2023

Fast Inference for Quantile Regression with Tens of Millions of Observations

Big data analytics has opened new avenues in economic research, but the challenge of analyzing datasets with tens of millions of observations is substantial. Conventional econometric methods based on extreme estimators require large amounts of computing resources and memory, which are often not readily available. In this paper, we focus on linear quantile regression applied to "ultra-large" datasets, such as U.S. decennial censuses. A fast inference framework is presented, utilizing stochastic subgradient descent (S-subGD) updates. The inference procedure handles cross-sectional data sequentially: (i) updating the parameter estimate with each incoming "new observation", (ii) aggregating it as a $\textit{Polyak-Ruppert}$ average, and (iii) computing a pivotal statistic for inference using only a solution path. The methodology draws from time-series regression to create an asymptotically pivotal statistic through random scaling. Our proposed test statistic is calculated in a fully online fashion and critical values are calculated without resampling. We conduct extensive numerical studies to showcase the computational merits of our proposed inference. For inference problems as large as $(n, d) \sim (10^7, 10^3)$, where $n$ is the sample size and $d$ is the number of regressors, our method generates new insights, surpassing current inference methods in computation. Our method specifically reveals trends in the gender gap in the U.S. college wage premium using millions of observations, while controlling over $10^3$ covariates to mitigate confounding effects.

econ.EM↗

arXiv2023

SGMM: Stochastic Approximation to Generalized Method of Moments

We introduce a new class of algorithms, Stochastic Generalized Method of Moments (SGMM), for estimation and inference on (overidentified) moment restriction models. Our SGMM is a novel stochastic approximation alternative to the popular Hansen (1982) (offline) GMM, and offers fast and scalable implementation with the ability to handle streaming datasets in real time. We establish the almost sure convergence, and the (functional) central limit theorem for the inefficient online 2SLS and the efficient SGMM. Moreover, we propose online versions of the Durbin-Wu-Hausman and Sargan-Hansen tests that can be seamlessly integrated within the SGMM framework. Extensive Monte Carlo simulations show that as the sample size increases, the SGMM matches the standard (offline) GMM in terms of estimation accuracy and gains over computational efficiency, indicating its practical value for both large-scale and online datasets. We demonstrate the efficacy of our approach by a proof of concept using two well known empirical examples with large sample sizes.

econ.EM↗

arXiv2023

Robust Inference on Infinite and Growing Dimensional Time Series Regression

We develop a class of tests for time series models such as multiple regression with growing dimension, infinite-order autoregression and nonparametric sieve regression. Examples include the Chow test and general linear restriction tests of growing rank $p$. Employing such increasing $p$ asymptotics, we introduce a new scale correction to conventional test statistics which accounts for a high-order long-run variance (HLV) that emerges as $ p $ grows with sample size. We also propose a bias correction via a null-imposed bootstrap to alleviate finite sample bias without sacrificing power unduly. A simulation study shows the importance of robustifying testing procedures against the HLV even when $ p $ is moderate. The tests are illustrated with an application to the oil regressions in Hamilton (2003).

econ.EM↗

arXiv2022

Minimax Risk in Estimating Kink Threshold and Testing Continuity

We derive a risk lower bound in estimating the threshold parameter without knowing whether the threshold regression model is continuous or not. The bound goes to zero as the sample size $ n $ grows only at the cube root rate. Motivated by this finding, we develop a continuity test for the threshold regression model and a bootstrap to compute its \textit{p}-values. The validity of the bootstrap is established, and its finite sample property is explored through Monte Carlo simulations.

econ.EM↗

arXiv2021

Fast and Robust Online Inference with Stochastic Gradient Descent via Random Scaling

We develop a new method of online inference for a vector of parameters estimated by the Polyak-Ruppert averaging procedure of stochastic gradient descent (SGD) algorithms. We leverage insights from time series regression in econometrics and construct asymptotically pivotal statistics via random scaling. Our approach is fully operational with online data and is rigorously underpinned by a functional central limit theorem. Our proposed inference method has a couple of key advantages over the existing methods. First, the test statistic is computed in an online fashion with only SGD iterates and the critical values can be obtained without any resampling methods, thereby allowing for efficient implementation suitable for massive online data. Second, there is no need to estimate the asymptotic variance and our inference method is shown to be robust to changes in the tuning parameters for SGD algorithms in simulation experiments with synthetic data.

stat.ML↗

arXiv2020

Factor-Driven Two-Regime Regression

We propose a novel two-regime regression model where regime switching is driven by a vector of possibly unobservable factors. When the factors are latent, we estimate them by the principal component analysis of a panel data set. We show that the optimization problem can be reformulated as mixed integer optimization, and we present two alternative computational algorithms. We derive the asymptotic distribution of the resulting estimator under the scheme that the threshold effect shrinks to zero. In particular, we establish a phase transition that describes the effect of first-stage factor estimation as the cross-sectional dimension of panel data increases relative to the time-series dimension. Moreover, we develop bootstrap inference and illustrate our methods via numerical studies.

econ.EM↗

arXiv2020

Frequent or Systematic Changes? discussion on "Detecting possibly frequent change-points: Wild Binary Segmentation 2 and steepest-drop model selection."

We discuss Fryzlewicz's (2020) that proposes WBS2.SDLL approach to detect possibly frequent changes in mean of a series. Our focus is on the potential issues related to the model misspecification. We present some numerical examples such as the self-exciting threshold autoregression and the unit root process, that can be confused as a frequent change-points model.

stat.ME↗

arXiv2020

Sparse HP Filter: Finding Kinks in the COVID-19 Contact Rate

In this paper, we estimate the time-varying COVID-19 contact rate of a Susceptible-Infected-Recovered (SIR) model. Our measurement of the contact rate is constructed using data on actively infected, recovered and deceased cases. We propose a new trend filtering method that is a variant of the Hodrick-Prescott (HP) filter, constrained by the number of possible kinks. We term it the $\textit{sparse HP filter}$ and apply it to daily data from five countries: Canada, China, South Korea, the UK and the US. Our new method yields the kinks that are well aligned with actual events in each country. We find that the sparse HP filter provides a fewer kinks than the $\ell_1$ trend filter, while both methods fitting data equally well. Theoretically, we establish risk consistency of both the sparse HP and $\ell_1$ trend filters. Ultimately, we propose to use time-varying $\textit{contact growth rates}$ to document and monitor outbreaks of COVID-19.

econ.EM↗

arXiv2020

Desperate times call for desperate measures: government spending multipliers in hard times

We investigate state-dependent effects of fiscal multipliers and allow for endogenous sample splitting to determine whether the US economy is in a slack state. When the endogenized slack state is estimated as the period of the unemployment rate higher than about 12 percent, the estimated cumulative multipliers are significantly larger during slack periods than non-slack periods and are above unity. We also examine the possibility of time-varying regimes of slackness and find that our empirical results are robust under a more flexible framework. Our estimation results point out the importance of the heterogenous effects of fiscal policy and shed light on the prospect of fiscal policy in response to economic shocks from the current COVID-19 pandemic.

econ.GN↗

arXiv2019

Estimation of Dynamic Panel Threshold Model using Stata

We develop a Stata command xthenreg to implement the first-differenced GMM estimation of the dynamic panel threshold model, which Seo and Shin (2016, Journal of Econometrics 195: 169-186) have proposed. Furthermore, We derive the asymptotic variance formula for a kink constrained GMM estimator of the dynamic threshold model and include an estimation algorithm. We also propose a fast bootstrap algorithm to implement the bootstrap for the linearity test. The use of the command is illustrated through a Monte Carlo simulation and an economic application.

econ.EM↗