Moment Restrictions Research Articles

Estimation for conditional moment models based on martingale difference divergence

We provide a new estimation method for conditional moment models via the martingale difference divergence (MDD). Our MDD‐based estimation method is formed in the framework of a continuum of unconditional moment restrictions. Unlike the existing estimation methods in this framework, the MDD‐based estimation method adopts a non‐integrable weighting function, which could capture more information from unconditional moment restrictions than the integrable weighting function to enhance the estimation efficiency. Due to the nature of shift‐invariance in MDD, our MDD‐based estimation method can not identify the intercept parameters. To overcome this identification issue, we further provide a two‐step estimation procedure for the model with intercept parameters. Under regularity conditions, we establish the asymptotics of the proposed estimators, which are not only easy‐to‐implement with expectation‐based asymptotic variances, but also applicable to time series data with an unspecified form of conditional heteroskedasticity. Finally, we illustrate the usefulness of the proposed estimators by simulations and two real examples.

A Pareto tail plot without moment restrictions

We propose a mean functional that exists for arbitrary probability distributions and characterizes the Pareto distribution within the set of distributions with finite left endpoint. This is in sharp contrast to the mean excess plot, which is meaningless for distributions without an existing mean and has non-standard behavior when the mean is finite, but the second moment does not exist. The construction of the plot is based on the principle of a single huge jump, which differentiates between distributions with moderately heavy and super heavy tails. We present an estimator of the tail function based on U-statistics and study its large sample properties. Several loss datasets illustrate the use of the new plot.

EFFICIENCY IN ESTIMATION UNDER MONOTONIC ATTRITION

Attrition is monotonic when agents leaving multi-period studies do not return. Under a general missing at random (MAR) assumption, we study efficiency in estimation of parameters defined by moment restrictions on the distributions of the counterfactuals that were unrealized due to monotonic attrition. We discuss novel issues related to overidentification, usability of sample units, and the information content of various MAR assumptions for estimation of such parameters. We propose a standard doubly robust estimator for these parameters by equating to zero the sample analog of their respective efficient influence functions. Our proposed estimator performs well and vastly outperforms other estimators in our simulation experiment and empirical illustration.

GMM estimation for high-dimensional panel data models

In this paper, we study a class of high dimensional moment restriction panel data models with interactive effects, where the factors are unobserved and these factor loadings are nonparametrically unknown smooth functions of individual characteristic variables. We allow the dimension of the parameter vector and the number of moment conditions to diverge with the sample size. This is a very general framework and is closely related to many existing linear and nonlinear panel data models. In order to estimate the unknown parameters, factors and factor loadings, we propose a sieve-based generalized method of moments estimation method and we show that under a set of simple identification conditions, all those unknown quantities can be consistently estimated. Further we establish asymptotic distributions of the proposed estimators. In addition, we propose tests for over-identification, specification of factor loading functions, and establish their large sample properties. Moreover, a number of simulation studies are conducted to examine the performance of the proposed estimators and test statistics in finite samples. An empirical example on stock return prediction is studied to demonstrate both the empirical relevance and the applicability of the proposed framework and corresponding estimation and testing methods.

Factor IV Estimation in Conditional Moment Models with an Application to Inflation Dynamics

Abstract In a conditional moment model, we develop a new integrated conditional moment (ICM) estimator which directly exploits factor-based conditional moment restrictions without having to first parametrize, or estimate such restrictions. We focus on a time series framework where the large number of available instruments and associated lags is driven by a relatively small number of unobserved factors. We build on the ICM principle originally proposed by Bierens (1982) and combine it with information reduction methods to handle the large number of potential instruments which may exceed the sample size. Under the maintained validity of the true factors, but not that of observed instruments, and standard regularity assumptions, our estimator is consistent, asymptotically normally distributed, and easy to compute. In our simulation studies, we document its reliability and power in cases where the underlying relationship between the endogenous variables and the instruments may be heterogeneous, non-linear, or even unstable over time. Our estimation of the New Keynesian Phillips curve with U.S. data reveals that forward- and backward-looking behaviors are quantitatively equally as important, while the driver’s role is nil.

INFERENCE IN PARTIALLY IDENTIFIED PANEL DATA MODELS WITH INTERACTIVE FIXED EFFECTS

In this paper, we develop methods for statistical inferences in a partially identified nonparametric panel data model with endogeneity and interactive fixed effects. Under some normalization rules, we can concentrate out the large-dimensional parameter vector of factor loadings and specify a set of conditional moment restrictions that are involved with only the finite-dimensional factor parameters along with the infinite-dimensional nonparametric component. For a conjectured restriction on the parameter, we consider testing the null hypothesis that the restriction is satisfied by at least one element in the identified set and propose a test statistic based on a novel martingale difference divergence measure for the distance between a conditional expectation object and zero. We derive a tight asymptotic distributional upper bound for the resultant test statistic under the null and show that it is divergent at rate-N under the global alternative. To obtain the critical values for our test, we propose a version of multiplier bootstrap and establish its asymptotic validity. Simulations demonstrate the finite sample properties of our inference procedure. We apply our method to study Engel curves for major nondurable expenditures in China by using a panel dataset from the China Family Panel Studies.

Specification testing for conditional moment restrictions under local identification failure

Specification testing for conditional moment restrictions under local identification failure

SGMM: Stochastic Approximation to Generalized Method of Moments

Abstract 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.

On vector linear double autoregression

This article proposes a vector linear double autoregressive (VLDAR) model with the constant conditional correlation specification, which can capture the co‐movement of multiple series and jointly model their conditional means and volatilities. The strict stationarity of the new model is discussed, and a self‐weighted Gaussian quasi‐maximum likelihood estimator (SQMLE) is proposed for estimation. To reduce the computational cost, especially when the series dimension is large, a block coordinate descent (BCD) algorithm is provided to calculate the SQMLE. Moreover, a Bayesian information criterion is introduced for order selection, and a multi‐variate mixed portmanteau test is constructed for checking the adequacy of fitted models. All asymptotic properties for estimation, model selection, and portmanteau test are established without any moment restrictions imposed on the data process, which makes the new model and its inference tools applicable for heavy‐tailed data. Simulation experiments are conducted to evaluate the finite‐sample performance of the proposed methodology, and an empirical example on analyzing S&P 500 sector indices is presented to illustrate the usefulness of the new model in contrast with competitors.

IDENTIFICATION AND INFERENCE IN A QUANTILE REGRESSION DISCONTINUITY DESIGN UNDER RANK SIMILARITY WITH COVARIATES

This study investigates the identification and inference of quantile treatment effects (QTEs) in a fuzzy regression discontinuity (RD) design under rank similarity. Unlike Frandsen et al. (2012, Journal of Econometrics 168, 382–395), who focus on QTEs only for the compliant subpopulation, our approach can identify QTEs and average treatment effect for the whole population at the threshold. We derived a new set of moment restrictions for the RD model by imposing a local rank similarity condition, which restricts the evolution of individual ranks across treatment status in a neighborhood around the threshold. Based on the moment restrictions, we derive closed-form solutions for the estimands of the potential outcome cumulative distribution functions for the whole population. We demonstrate the functional central limit theorems and bootstrap validity results for the QTE estimators by explicitly accounting for observed covariates. In particular, we develop a multiplier bootstrap-based inference method with robustness against large bandwidths that applies to uniform inference by extending the recent work of Chiang et al. (2019, Journal of Econometrics 211, 589–618). We also propose a test for the local rank similarity assumption. To illustrate the estimation approach and its properties, we provide a simulation study and estimate the impacts of India’s 40-billion-dollar national rural road construction program on the reallocation of labor out of agriculture.

Dynamic Autoregressive Liquidity (DArLiQ)

We introduce a new class of semiparametric dynamic autoregressive models for the Amihud illiquidity measure, which captures both the long-run trend in the illiquidity series with a nonparametric component and the short-run dynamics with an autoregressive component. We develop a generalized method of moments (GMM) estimator based on conditional moment restrictions and an efficient semiparametric maximum likelihood (ML) estimator based on an iid assumption. We derive large sample properties for our estimators. Finally, we demonstrate the model fitting performance and its empirical relevance on an application. We investigate how the different components of the illiquidity process obtained from our model relate to the stock market risk premium using data on the S&P 500 stock market index.

Robust Causal Graph Representation Learning against Confounding Effects

The prevailing graph neural network models have achieved significant progress in graph representation learning. However, in this paper, we uncover an ever-overlooked phenomenon: the pre-trained graph representation learning model tested with full graphs underperforms the model tested with well-pruned graphs. This observation reveals that there exist confounders in graphs, which may interfere with the model learning semantic information, and current graph representation learning methods have not eliminated their influence. To tackle this issue, we propose Robust Causal Graph Representation Learning (RCGRL) to learn robust graph representations against confounding effects. RCGRL introduces an active approach to generate instrumental variables under unconditional moment restrictions, which empowers the graph representation learning model to eliminate confounders, thereby capturing discriminative information that is causally related to downstream predictions. We offer theorems and proofs to guarantee the theoretical effectiveness of the proposed approach. Empirically, we conduct extensive experiments on a synthetic dataset and multiple benchmark datasets. Experimental results demonstrate the effectiveness and generalization ability of RCGRL. Our codes are available at https://github.com/hang53/RCGRL.

Information Equivalence among Transformations of Semi‐parametric Nonlinear Panel Data Models*

AbstractThis paper considers transformations of nonlinear semi‐parametric mean functions that yield moment conditions for estimation. Such transformations are said to be information equivalent if they yield the same asymptotic efficiency bound. I derive a unified theory of algebraic equivalence for moment conditions created by a given linear transformation. The main equivalence result states that under standard regularity conditions, transformations that create conditional moment restrictions in a given empirical setting need only to have an equal rank to reach the same efficiency bound. I compare feasible and infeasible transformations of both nonlinear models with multiplicative heterogeneity and linear models with unobserved factor structures.

Instrumental variable regression via kernel maximum moment loss

AbstractWe investigate a simple objective for nonlinear instrumental variable (IV) regression based on a kernelized conditional moment restriction known as a maximum moment restriction (MMR). The MMR objective is formulated by maximizing the interaction between the residual and the instruments belonging to a unit ball in a reproducing kernel Hilbert space. First, it allows us to simplify the IV regression as an empirical risk minimization problem, where the risk function depends on the reproducing kernel on the instrument and can be estimated by aU-statistic orV-statistic. Second, on the basis this simplification, we are able to provide consistency and asymptotic normality results in both parametric and nonparametric settings. Finally, we provide easy-to-use IV regression algorithms with an efficient hyperparameter selection procedure. We demonstrate the effectiveness of our algorithms using experiments on both synthetic and real-world data.

Reprint of: Initial conditions and moment restrictions in dynamic panel data models

Estimation of the dynamic error components model is considered using two alternative linear estimators that are designed to improve the properties of the standard first-differenced GMM estimator. Both estimators require restrictions on the initial conditions process. Asymptotic efficiency comparisons and Monte Carlo simulations for the simple AR(1) model demonstrate the dramatic improvement in performance of the proposed estimators compared to the usual first-differenced GMM estimator, and compared to non-linear GMM. The importance of these results is illustrated in an application to the estimation of a labour demand model using company panel data.

Fixed‐effects binary choice models with three or more periods

We consider fixed‐effects binary choice models with a fixed number of periods T and regressors without a large support. If the time‐varying unobserved terms are i.i.d. with known distribution F, Chamberlain (2010) shows that the common slope parameter is point identified if and only if F is logistic. However, he only considers in his proof T = 2. We show that the result does not generalize to T ≥ 3: the common slope parameter can be identified when F belongs to a family including the logit distribution. Identification is based on a conditional moment restriction. Under restrictions on the covariates, these moment conditions lead to point identification of relative effects. If T = 3 and mild conditions hold, GMM estimators based on these conditional moment restrictions reach the semiparametric efficiency bound. Finally, we illustrate our method by revisiting Brender and Drazen (2008).

Constrained Conditional Moment Restriction Models

Shape restrictions have played a central role in economics as both testable implications of theory and sufficient conditions for obtaining informative counterfactual predictions. In this paper, we provide a general procedure for inference under shape restrictions in identified and partially identified models defined by conditional moment restrictions. Our test statistics and proposed inference methods are based on the minimum of the generalized method of moments (GMM) objective function with and without shape restrictions. Uniformly valid critical values are obtained through a bootstrap procedure that approximates a subset of the true local parameter space. In an empirical analysis of the effect of childbearing on female labor supply, we show that employing shape restrictions in linear instrumental variables (IV) models can lead to shorter confidence regions for both local and average treatment effects. Other applications we discuss include inference for the variability of quantile IV treatment effects and for bounds on average equivalent variation in a demand model with general heterogeneity.

LARGE SAMPLE JUSTIFICATIONS FOR THE BAYESIAN EMPIRICAL LIKELIHOOD

This study investigates the asymptotic properties of the Bayesian empirical likelihood (BEL), which uses the empirical likelihood as an alternative to a parametric likelihood for Bayesian inference. We establish two asymptotic equivalence results based on the Bernstein–von Mises (BvM) theorem by introducing a new formulation of the moment restriction model. First, the limiting posterior distribution of the BEL is the same as that of a parametric Bayesian method that uses the likelihood of a least favorable model of the moment restriction model. Second, the limiting posterior distribution is also the same as that of a semiparametric Bayesian method that places priors on both a finite-dimensional parameter of interest and an infinite-dimensional nuisance parameter. Because parametric and semiparametric Bayesian methods are legitimate Bayesian procedures, the equivalence results provide a large sample justification for the BEL as a Bayesian inference method. Moreover, the BvM theorem provides a frequentist justification for BEL posterior inference.

TESTING A CLASS OF SEMI- OR NONPARAMETRIC CONDITIONAL MOMENT RESTRICTION MODELS USING SERIES METHODS

This paper proposes a new test for a class of conditional moment restrictions (CMRs) whose parameterization involves unknown, unrestricted conditional expectation functions. Motivating examples of such CMRs arise from models of discrete choice under uncertainty including certain static games of incomplete information. The proposed test may be viewed as a semi-/nonparametric extension of the Bierens (1982, Journal of Econometrics 20, 105–134) goodness-of-fit test of a parametric model for the conditional mean. Estimating conditional expectations using series methods and employing a Gaussian multiplier bootstrap to obtain critical values, the test is shown to be asymptotically correctly sized and consistent. Simulation studies indicate good finite-sample properties. In an empirical application, the test is used to study the validity of a game-theoretical model for discount store market entry, treating equilibrium beliefs as nonparametric conditional expectations. The test indicates that Walmart and Kmart entry decisions do not result from a static discrete game of incomplete information with linearly specified profits.

The moment restrictions for the durable consumption model with recursive utility revisited

A key assumption behind the moment restrictions for the durable consumption model with recursive utility is that a condition called normalization holds for the intertemporal marginal rate of substitution. This paper points out that one of the moment restrictions used in the literature is inconsistent with the assumption that this condition and the first-order conditions hold simultaneously. It shows that a two-step estimation procedure can avoid this issue. The method is illustrated with US data.