scholarly journals On uniform asymptotic risk of averaging GMM estimators

10.3982/qe711 ◽  
2019 ◽  
Vol 10 (3) ◽  
pp. 931-979 ◽  
Author(s):  
Xu Cheng ◽  
Zhipeng Liao ◽  
Ruoyao Shi
Keyword(s):  
Nonlinear Models ◽  
Sufficient Conditions ◽  
Risk Difference ◽  
Upper And Lower Bounds ◽  
Quadratic Loss ◽  
Finite Sample ◽  
Moment Conditions ◽  
Gmm Estimator ◽  
Asymptotic Risk ◽  
Non Gaussian

This paper studies the averaging GMM estimator that combines a conservative GMM estimator based on valid moment conditions and an aggressive GMM estimator based on both valid and possibly misspecified moment conditions, where the weight is the sample analog of an infeasible optimal weight. We establish asymptotic theory on uniform approximation of the upper and lower bounds of the finite‐sample truncated risk difference between any two estimators, which is used to compare the averaging GMM estimator and the conservative GMM estimator. Under some sufficient conditions, we show that the asymptotic lower bound of the truncated risk difference between the averaging estimator and the conservative estimator is strictly less than zero, while the asymptotic upper bound is zero uniformly over any degree of misspecification. The results apply to quadratic loss functions. This uniform asymptotic dominance is established in non‐Gaussian semiparametric nonlinear models.

GLOBAL IDENTIFICATION IN NONLINEAR MODELS WITH MOMENT RESTRICTIONS

2012 ◽  
Vol 28 (4) ◽  
pp. 719-729 ◽  
Author(s):  
Ivana Komunjer
Keyword(s):  
Finite Number ◽  
Nonlinear Models ◽  
Sufficient Conditions ◽  
Moment Conditions ◽  
Global Identification ◽  
The Moment ◽  
Moment Restrictions ◽  
Parameters Of Interest

This paper derives sufficient conditions for global identification in nonlinear models characterized by a finite number of unconditional moment restrictions. The main contribution of this paper is to provide a set of assumptions that are alternative to those of Gale-Nikaidô-Fisher-Rothenberg, and which when satisfied guarantee that the moment conditions globally identify the parameters of interest.

REDUNDANCY OF MOMENT CONDITIONS AND THE EFFICIENCY OF OLS IN SUR MODELS

2008 ◽  
Vol 24 (5) ◽  
pp. 1456-1460 ◽  
Author(s):  
Hailong Qian
Keyword(s):  
Least Squares ◽  
Asymptotic Efficiency ◽  
Generalized Method Of Moments ◽  
Sufficient Conditions ◽  
Generalized Least Squares ◽  
Ordinary Least Squares ◽  
American Statistical Association ◽  
Orthogonality Condition ◽  
Moment Conditions ◽  
Necessary And Sufficient

In this note, based on the generalized method of moments (GMM) interpretation of the usual ordinary least squares (OLS) and feasible generalized least squares (FGLS) estimators of seemingly unrelated regressions (SUR) models, we show that the OLS estimator is asymptotically as efficient as the FGLS estimator if and only if the cross-equation orthogonality condition is redundant given the within-equation orthogonality condition. Using the condition for redundancy of moment conditions of Breusch, Qian, Schmidt, and Wyhowski (1999, Journal of Econometrics 99, 89–111), we then derive the necessary and sufficient condition for the equal asymptotic efficiency of the OLS and FGLS estimators of SUR models. We also provide several useful sufficient conditions for the equal asymptotic efficiency of OLS and FGLS estimators that can be interpreted as various mixings of the two famous sufficient conditions of Zellner (1962, Journal of the American Statistical Association 57, 348–368).

A DELAY-DEPENDENT APPROACH TO ROBUST TAKAGI–SUGENO FUZZY CONTROL OF UNCERTAIN RECURRENT NEURAL NETWORKS WITH MIXED INTERVAL TIME-VARYING DELAYS

2011 ◽  
Vol 20 (08) ◽  
pp. 1571-1589 ◽  
Author(s):  
K. H. TSENG ◽  
J. S. H. TSAI ◽  
C. Y. LU
Keyword(s):  
Fuzzy Control ◽  
Time Delays ◽  
Sufficient Conditions ◽  
Upper And Lower Bounds ◽  
Linear Matrix ◽  
Uncertain Parameters ◽  
Time Varying ◽  
Interval Time ◽  
Delay Dependent ◽  
Takagi Sugeno

This paper deals with the problem of globally delay-dependent robust stabilization for Takagi–Sugeno (T–S) fuzzy neural network with time delays and uncertain parameters. The time delays comprise discrete and distributed interval time-varying delays and the uncertain parameters are norm-bounded. Based on Lyapunov–Krasovskii functional approach and linear matrix inequality technique, delay-dependent sufficient conditions are derived for ensuring the exponential stability for the closed-loop fuzzy control system. An important feature of the result is that all the stability conditions are dependent on the upper and lower bounds of the delays, which is made possible by using the proposed techniques for achieving delay dependence. Another feature of the results lies in that involves fewer matrix variables. Two illustrative examples are exploited in order to illustrate the effectiveness of the proposed design methods.

Near Observational Equivalence and Theoretical size Problems with Unit Root Tests

1996 ◽  
Vol 12 (4) ◽  
pp. 724-731 ◽  
Author(s):  
Jon Faust
Keyword(s):  
Unit Root ◽  
Sufficient Conditions ◽  
Unit Root Test ◽  
Asymptotic Distributions ◽  
Unit Root Tests ◽  
Finite Sample ◽  
Test Procedures ◽  
Asymptotic Size ◽  
Finite Sample Size ◽  
Topological Sense

Said and Dickey (1984,Biometrika71, 599–608) and Phillips and Perron (1988,Biometrika75, 335–346) have derived unit root tests that have asymptotic distributions free of nuisance parameters under very general maintained models. Under models as general as those assumed by these authors, the size of the unit root test procedures will converge to one, not the size under the asymptotic distribution. Solving this problem requires restricting attention to a model that is small, in a topological sense, relative to the original. Sufficient conditions for solving the asymptotic size problem yield some suggestions for improving finite-sample size performance of standard tests.

scholarly journals Studying State Convergence of Input-to-State Stable Systems with Applications to Power System Analysis

Energies ◽  
2019 ◽  
Vol 13 (1) ◽  
pp. 92 ◽  
Author(s):  
Antonio T. Alexandridis
Keyword(s):  
Nonlinear Systems ◽  
Power Systems ◽  
Power System ◽  
System Analysis ◽  
Nonlinear Models ◽  
Sufficient Conditions ◽  
Stability And Convergence ◽  
Convergence To Equilibrium ◽  
Analysis Tool ◽  
Wide Range

In stability studies, the response of a system enforced by external, known or unknown, inputs is of great importance. Although such an analysis is quite easy for linear systems, it becomes a cumbersome task when nonlinearities exist in the system model. Nevertheless, most of the real-world systems are externally enforced nonlinear systems with nonzero equilibriums. Representative examples in this category include power systems, where studies on stability and convergence to equilibrium constitute crucial objectives. Driven by this need, the aim of the present work is twofold: First, to substantially complete the theoretical infrastructure by establishing globally valid sufficient conditions for externally enforced nonlinear systems that converge to nonzero equilibriums and, second, to deploy an efficient method easily applicable on practical problems as it is analyzed in detail on a typical power system example. To that end, in the theoretical first part of the paper, a rigorous nonlinear analysis is developed. Particularly, starting from the well-established nonlinear systems theory based on Lyapunov techniques and on the input-to-state stability (ISS) notion, it is proven after a systematic and lengthy analysis that ISS can also guarantee convergence to nonzero equilibrium. Two theorems and two corollaries are established to provide the sufficient conditions. As shown in the paper, the main stability and convergence objectives for externally enforced systems are fulfilled if simple exponential or asymptotic converging conditions can be proven for the unforced system. Then, global or local convergence is established, respectively, while for the latter case, a novel method based on a distance-like measure for determining the region of attraction (RoA) is proposed. The theoretical results are examined on classic power system generation nonlinear models. The power system examples are suitably selected in order to effectively demonstrate the proposed method as a stability analysis tool and to validate all the particular steps, especially that of evaluating the RoA. The examined system results clearly verify the theoretical part, indicating a rather wide range of applications in power systems.

scholarly journals Distributed simultaneous localization and mapping for mobile robot networks via hybrid dynamic belief propagation

2017 ◽  
Vol 13 (8) ◽  
pp. 155014771772671
Author(s):  
Jiuqing Wan ◽  
Shaocong Bu ◽  
Jinsong Yu ◽  
Liping Zhong
Keyword(s):  
Mobile Robot ◽  
Posterior Probability ◽  
Belief Propagation ◽  
Nonlinear Models ◽  
Simultaneous Localization And Mapping ◽  
Factor Graph ◽  
Posterior Probability Distribution ◽  
Localization And Mapping ◽  
Nonparametric Techniques ◽  
Non Gaussian

This article proposes a hybrid dynamic belief propagation for simultaneous localization and mapping in the mobile robot network. The positions of landmarks and the poses of moving robots at each time slot are estimated simultaneously in an online and distributed manner, by fusing the odometry data of each robot and the measurements of robot–robot or robot–landmark relative distance and angle. The joint belief state of all robots and landmarks is encoded by a factor graph and the marginal posterior probability distribution of each variable is inferred by belief propagation. We show how to calculate, broadcast, and update messages between neighboring nodes in the factor graph. Specifically, we combine parametric and nonparametric techniques to tackle the problem arisen from non-Gaussian distributions and nonlinear models. Simulation and experimental results on publicly available dataset show the validity of our algorithm.

On the rate of convergence of probabilities of moderate deviations

1970 ◽  
Vol 11 (1) ◽  
pp. 91-94 ◽  
Author(s):  
V. K. Rohatgi
Keyword(s):  
Sufficient Conditions ◽  
Moderate Deviations ◽  
Independent Random Variables ◽  
Standard Normal Distribution ◽  
Positive Real ◽  
Moment Conditions ◽  
Standard Normal ◽  
Image Position ◽  
Necessary And Sufficient ◽  
Asymptotic Forms

Let {Xn: n ≧ 1} be a sequence of independent random variables and write Letand let . Suppose that converges in law to the standard normal distribution (see [5, 280] for necessary and sufficient conditions). Let {xn} be a monotonic sequence of positive real numbers such that xn → ∞ as n → ∞. Then as n → ∞ for all ε > 0. [6] Rubin and Sethuraman call probabilities of the form probabilities of moderate deviations and obtain asymptotic forms for such probabilities under appropriate moment conditions.

On characterizing the set of martingale measures in discrete time

2015 ◽  
Vol 15 (03) ◽  
pp. 1550017 ◽  
Author(s):  
Abdelkarem Berkaoui
Keyword(s):  
Discrete Time ◽  
Sufficient Conditions ◽  
Sample Space ◽  
Probability Measures ◽  
Finite Sample ◽  
Martingale Measures ◽  
Space Case ◽  
Necessary And Sufficient ◽  
Adapted Process ◽  
Vector Valued

We state necessary and sufficient conditions on a set of probability measures to be the set of martingale measures for a vector valued, bounded and adapted process. In the absence of the maximality condition, we prove the existence of the smallest set of martingale measures. We apply such results to the finite sample space case.

The Influence of Alternative Wave Loading and Support Modeling Assumptions on Jack-Up Rig Response Extremes

1996 ◽  
Vol 118 (2) ◽  
pp. 109-114 ◽  
Author(s):  
L. Manuel ◽  
C. A. Cornell
Keyword(s):  
Nonlinear Models ◽  
Random Wave ◽  
Force Model ◽  
Wave Loading ◽  
Force Modeling ◽  
Hydrodynamic Damping ◽  
Extreme Response ◽  
The Absolute ◽  
Non Gaussian ◽  
Jack Up

A study is conducted of the response of a jack-up rig to random wave loading. Steady current and wind load effects are also included. The effects of varying the relative motion assumption (in the Morison equation) and of varying the bottom fixity assumptions are investigated. One “fixity” model employs nonlinear soil springs. Time domain simulations are performed using linearized as well as fully nonlinear models for the jack-up rig. Comparisons of response statistics are made for two seastates. Hydrodynamic damping causes the rms response to be lower in the relative Morison case. The absence of this source of damping in the absolute Morison force model gives rise to larger resonance/dynamic effects—this tends to “Gaussianize” the response. Hence, the relative Morison model leads to stronger non-Gaussian behavior than the absolute Morison model. This is reflected in moments as well as extremes. The different support conditions studied are seen to significantly influence extreme response estimates. In general, stiffer models predict smaller rms response estimates, but also exhibit stronger non-Gaussian behavior. The choice of the Morison force modeling assumption (i.e., the relative versus the absolute motion formulation) is seen to have at least a secondary role in influencing response moments and extremes.

scholarly journals ON THE ASYMPTOTIC EFFICIENCY OF GMM

2013 ◽  
Vol 30 (2) ◽  
pp. 372-406 ◽  
Author(s):  
Marine Carrasco ◽  
Jean-Pierre Florens
Keyword(s):  
Reproducing Kernel ◽  
Reproducing Kernel Hilbert Space ◽  
Asymptotic Variance ◽  
Inner Product ◽  
Method Of Moment ◽  
Conditional Moment ◽  
Moment Conditions ◽  
Gmm Estimator ◽  
The Moment ◽  
Semiparametric Efficiency Bound

The efficiency of the generalized method of moment (GMM) estimator is addressed by using a characterization of its variance as an inner product in a reproducing kernel Hilbert space. We show that the GMM estimator is asymptotically as efficient as the maximum likelihood estimator if and only if the true score belongs to the closure of the linear space spanned by the moment conditions. This result generalizes former ones to autocorrelated moments and possibly infinite number of moment restrictions. Second, we derive the semiparametric efficiency bound when the observations are known to be Markov and satisfy a conditional moment restriction. We show that it coincides with the asymptotic variance of the optimal GMM estimator, thus extending results by Chamberlain (1987,Journal of Econometrics34, 305–33) to a dynamic setting. Moreover, this bound is attainable using a continuum of moment conditions.

Sign in / Sign up

Export Citation Format

Share Document