Xiaohong Chen Publications

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.

We introduce two data-driven procedures for optimal estimation and inference in nonparametric models using instrumental variables. The first is a data-driven choice of sieve dimension for a popular class of sieve two-stage least-squares estimators. When implemented with this choice, estimators of both the structural function h₀ and its derivatives (such as elasticities) converge at the fastest possible (i.e. minimax) rates in sup-norm. The second is for constructing uniform confidence bands (UCBs) for h₀ and its derivatives. Our UCBs guarantee coverage over a generic class of data-generating processes and contract at the minimax rate, possibly up to a logarithmic factor. As such, our UCBs are asymptotically more efficient than UCBs based on the usual approach of undersmoothing. As an application, we estimate the elasticity of the intensive margin of firm exports in a monopolistic competition model of international trade. Simulations illustrate the good performance of our procedures in empirically calibrated designs. Our results provide evidence against common parameterizations of the distribution of unobserved firm heterogeneity.

We develop a state-space model with a transition equation that takes the form of a functional vector autoregression (VAR) and stacks macroeconomic aggregates and a cross-sectional density. The measurement equation captures the error in estimating log densities from repeated cross-sectional samples. The log densities and their transition kernels are approximated by sieves, which leads to a finite-dimensional VAR for macroeconomic aggregates and sieve coefficients. With this model, we study the dynamics of technology shocks, GDP (gross domestic product), employment, and the earnings distribution. We find that spillovers between aggregate and distributional dynamics are generally small, that a positive technology shock tends to decrease inequality, and that a shock that raises earnings inequality leads to a small and insignificant GDP response.

We propose a new adaptive hypothesis test for inequality (e.g., monotonicity, convexity) and equality (e.g., parametric, semiparametric) restrictions on a structural function in a nonparametric instrumental variables (NPIV) model. Our test statistic is based on a modified leave-one-out sample analog of a quadratic distance between the restricted and unrestricted sieve two-stage least squares estimators. We provide computationally simple, data-driven choices of sieve tuning parameters and Bonferroni adjusted chi-squared critical values. Our test adapts to the unknown smoothness of alternative functions in the presence of unknown degree of endogeneity and unknown strength of the instruments. It attains the adaptive minimax rate of testing in L². That is, the sum of the supremum of type I error over the composite null and the supremum of type II error over nonparametric alternative models cannot be minimized by any other tests for NPIV models of unknown regularities. Confidence sets in L² are obtained by inverting the adaptive test. Simulations confirm that, across different strength of instruments and sample sizes, our adaptive test controls size and its finite-sample power greatly exceeds existing non-adaptive tests for monotonicity and parametric restrictions in NPIV models. Empirical applications to test for shape restrictions of differentiated products demand and of Engel curves are presented.

This paper considers estimation of short-run dynamics in time series that contain a nonstationary component. We assume that appropriate preliminary methods can be applied to the observed time series to separate short-run elements from long-run slowly evolving secular components, and focus on estimation of the short-run dynamics based on the filtered data. We use a flexible copula-generated Markov model to capture the nonlinear temporal dependence in the short-run component and study estimation of the copula model. Using the rescaled empirical distribution of the filtered data as an estimator of the marginal distribution, Chen et al. (2022) proposed a simple, yet flexible, two-step estimation procedure for the copula model. The two-step estimator works well when the tail dependence is small. However, simulations reveal that the two-step estimator may be biased in finite samples in the presence of tail dependence. To improve the performance of short-term dynamic analysis in the presence of tail dependence, we propose in this paper a pseudo sieve maximum likelihood (PSML) procedure to jointly estimate the residual copula parameter and the invariant density of the filtered residuals. We establish the root-consistency and asymptotic distribution of the PSML estimator of any smooth functional of the residual copula parameter and invariant residual density. We further show that the PSML estimator of the residual copula parameter is asymptotically normal, with the limiting distribution independent of the filtration. Simulations reveal that in the presence of strong tail dependence, compared to the two-step estimates of Chen et al. (2022), the proposed PSML estimates have smaller biases and smaller mean squared errors even in small samples. Applications to nonstationary macro-finance and climate time series are presented.

Semiparametric efficient estimation of various multi-valued causal effects, including quantile treatment effects, is important in economic, biomedical, and other social sciences. Under the unconfoundedness condition, adjustment for confounders requires estimating the nuisance functions relating outcome or treatment to confounders nonparametrically. This paper considers a generalized optimization framework for efficient estimation of general treatment effects using artificial neural networks (ANNs) to approximate the unknown nuisance function of growing-dimensional confounders. We establish a new approximation error bound for the ANNs to the nuisance function belonging to a mixed smoothness class without a known sparsity structure. We show that the ANNs can alleviate the “curse of dimensionality” under this circumstance. We establish the root- consistency and asymptotic normality of the proposed general treatment effects estimators, and apply a weighted bootstrap procedure for conducting inference. The proposed methods are illustrated via simulation studies and a real data application.

Springer | August 2012 | ISBN: 1461416523

(Edited with Norman R. Swanson) This book is a collection of articles that present the most recent cutting edge results on specification and estimation of economic models written by a number of the world’s foremost leaders in the fields of theoretical and methodological econometrics. Recent advances in asymptotic approximation theory, including the use of higher order asymptotics for things like estimator bias correction, and the use of various expansion and other theoretical tools for the development of bootstrap techniques designed for implementation when carrying out inference are at the forefront of theoretical development in the field of econometrics. One important feature of these advances in the theory of econometrics is that they are being seamlessly and almost immediately incorporated into the “empirical toolbox” that applied practitioners use when actually constructing models using data, for the purposes of both prediction and policy analysis and the more theoretically targeted chapters in the book will discuss these developments. Turning now to empirical methodology, chapters on prediction methodology will focus on macroeconomic and financial applications, such as the construction of diffusion index models for forecasting with very large numbers of variables, and the construction of data samples that result in optimal predictive accuracy tests when comparing alternative prediction models. Chapters carefully outline how applied practitioners can correctly implement the latest theoretical refinements in model specification in order to “build” the best models using large-scale and traditional datasets, making the book of interest to a broad readership of economists from theoretical econometricians to applied economic practitioners.