About

Wei "Wayne" Chen is an Assistant Professor in the Department of Mechanical Engineering at Texas A&M University. He holds a Ph.D. in Mechanical Engineering from the University of Maryland, College Park, obtained in 2019, and both his M.S. and B.S. degrees in Mechanical Engineering from Chongqing University in China, earned in 2015 and 2012 respectively. His research interests include generative design, artificial intelligence and machine learning, uncertainty quantification, and advanced manufacturing. Chen has received several awards and honors, such as the ASME Journal of Mechanical Design Reviewer of the Year Award in 2023, the ASME DAC Best Paper Award in 2022, and an Editors’ Choice Honorable Mention from the Journal of Mechanical Design in 2021. His scholarly work involves developing innovative computational methods and models to support engineering design, with a focus on leveraging AI and data-driven approaches to improve design processes and material functionalities.

Research topics

• Mathematics
• Statistics
• Applied mathematics
• Econometrics
• Algorithm

Selected publications

• Subsampling based inference for<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="mml31" display="inline" overflow="scroll" altimg="si31.gif"><mml:mi>U</mml:mi></mml:math>statistics under thick tails using self-normalization

  Statistics & Probability Letters · 2018-03-08

  article1st authorCorresponding
  PublisherDOI

• Uniform Inference in Predictive Regression Models

  Journal of Business and Economic Statistics · 2013-10-01

  article1st authorCorresponding

  The restricted likelihood has been found to provide a well-behaved likelihood ratio test in the predictive regression model even when the regressor variable exhibits almost unit root behavior. Using the weighted least squares approximation to the restricted likelihood obtained in Chen and Deo, we provide a quasi restricted likelihood ratio test (QRLRT), obtain its asymptotic distribution as the nuisance persistence parameter varies, and show that this distribution varies very slightly. Consequently, the resulting sup bound QRLRT is shown to maintain size uniformly over the parameter space without sacrificing power. In simulations, the QRLRT is found to deliver uniformly higher power than competing procedures with power gains that are substantial.

  PublisherDOI

• The restricted likelihood ratio test for autoregressive processes

  Journal of Time Series Analysis · 2011-11-29 · 9 citations

  article1st authorCorresponding

  The restricted likelihood is known to produce estimates with significantly less bias in AR( p ) models with intercept and/or trend. In AR(1) models, the corresponding restricted likelihood ratio test (RLRT), unlike the t ‐statistic or the usual LRT, has been recently shown to be well approximated by the chi‐square distribution even close to the unit root, thus yielding confidence intervals with good coverage properties. In this article, we extend this result to AR( p ) processes of arbitrary order p by obtaining the expansion of the RLRT distribution around that of the limiting chi‐squared and showing that the error is bounded even as the unit root is approached. Next, we investigate the correspondence between the AR coefficients and the partial autocorrelations, which is well known in the stationary region, and extend to the more general situation of potentially multiple unit roots. In the case of one positive unit root, which is of most practical interest, the resulting parameter space is shown to be the bounded p ‐dimensional hypercube (−1, 1] × (−1, 1) p −1 . This simple parameter space, in addition with a stable algorithm that we provide for computing the restricted likelihood, allows its easy computation and optimization as well as construction of confidence intervals for the sum of the AR coefficients. In simulations, the RLRT intervals are shown to have not only near exact coverage in keeping with our theoretical results, but also shorter lengths and significantly higher power against stationary alternatives than other competing interval procedures. An application to the well‐known Nelson–Plosser data yields RLRT based intervals that can be markedly different from those in the literature.

  PublisherDOI

• Efficiency in estimation of memory

  Journal of Statistical Planning and Inference · 2010-05-06 · 2 citations

  article1st authorCorresponding
  PublisherDOI

• The restricted likelihood ratio test at the boundary in autoregressive series

  Journal of Time Series Analysis · 2009-09-15 · 7 citations

  article1st authorCorresponding

  Abstract. The restricted likelihood ratio test, RLRT, for the autoregressive coefficient in autoregressive models has recently been shown to be second‐order pivotal when the autoregressive coefficient is in the interior of the parameter space and so is very well approximated by the distribution. In this article, the non‐standard asymptotic distribution of the RLRT for the unit root boundary value is obtained and is found to be almost identical to that of the in the right tail. Together, these two results imply that the distribution approximates the RLRT distribution very well even for near unit root series and transitions smoothly to the unit root distribution.

  PublisherDOI

• Fractional Cointegration

  2009-01-01 · 4 citations

  book-chapter1st authorCorresponding
  PublisherDOI

• BIAS REDUCTION AND LIKELIHOOD-BASED ALMOST EXACTLY SIZED HYPOTHESIS TESTING IN PREDICTIVE REGRESSIONS USING THE RESTRICTED LIKELIHOOD

  Econometric Theory · 2009-09-03 · 38 citations

  article1st author

  Difficulties with inference in predictive regressions are generally attributed to strong persistence in the predictor series. We show that the major source of the problem is actually the nuisance intercept parameter, and we propose basing inference on the restricted likelihood, which is free of such nuisance location parameters and also possesses small curvature, making it suitable for inference. The bias of the restricted maximum likelihood (REML) estimates is shown to be approximately 50% less than that of the ordinary least squares (OLS) estimates near the unit root, without loss of efficiency. The error in the chi-square approximation to the distribution of the REML-based likelihood ratio test (RLRT) for no predictability is shown to be $({\textstyle{3 \over 4}} - \rho ^2)n^{ - 1} (G_3 (\cdot) - G_1 (\cdot)) + O(n^{ - 2}),$ where | ρ | &lt; 1 is the correlation of the innovation series and G s (·) is the cumulative distribution function (c.d.f.) of a $\chi _s^2 $ random variable. This very small error, free of the autoregressive (AR) parameter, suggests that the RLRT for predictability has very good size properties even when the regressor has strong persistence. The Bartlett-corrected RLRT achieves an O ( n −2 ) error. Power under local alternatives is obtained, and extensions to more general univariate regressors and vector AR(1) regressors, where OLS may no longer be asymptotically efficient, are provided. In simulations the RLRT maintains size well, is robust to nonnormal errors, and has uniformly higher power than the Jansson and Moreira (2006, Econometrica 74, 681–714) test with gains that can be substantial. The Campbell and Yogo (2006, Journal of Financial Econometrics 81, 27–60) Bonferroni Q test is found to have size distortions and can be significantly oversized.

  PublisherDOI

• The Restricted Likelihood Ratio Test at the Boundary in Autoregressive Series

  The Faculty Digital Archive (New York University) · 2009-08-01

  articleOpen access1st authorCorresponding

  The restricted likelihood ratio test, RLRT, for the autoregressive coefficient in autoregressive models has recently been shown to be second order pivotal when the autoregressive coefficient is in the interior of the parameter space and so is very well approximated by the chi-square distribution. In this paper, the non-standard asymptotic distribution of the RLRT for the unit root boundary value is obtained and is found to be almost identical to that of the chi-square in the right tail. Together, the above two results imply that the chi-square distribution approximates the RLRT distribution very well even for near unit root series and transitions smoothly to the unit root distribution.

  PublisherOA PDF

• Analysis of Integrated and Cointegrated Time Series with R, 2nd Edition

  Journal of Time Series Analysis · 2009-08-21 · 9 citations

  article1st authorCorresponding
  PublisherDOI

• Bias Reduction and Likelihood Based Almost-Exactly Sized Hypothesis Testing in Predestricted Likelihoodictive Regressions using the R

  The Faculty Digital Archive (New York University) · 2009-08-24

  articleOpen access1st authorCorresponding

  Difficulties with inference in predictive regressions are generally attributed to strong persistence in the predictor series. We show that the major source of the problem is actually the nuisance intercept parameter and propose basing inference on the Restricted Likelihood,which is free of such nuisance location parameters and also possesses small curvature, making it suitable for inference. The bias of the Restricted Maximum Likelihood (REML) estimates is shown to be approximately 50% less than that of the OLS estimates near the unit root, without loss of efficiency. The error in the chi-square approximation to the distribution of the REML based Likelihood Ratio Test (RLRT) for no predictability is shown to be 3/4 − ρ2 n−1 (G3 (·) − G1 (·)) + O n−2 , where |ρ| < 1 is the correlation of the innovation series and Gs (·) is the c.d.f. of a χ2s random variable. This very small error, free of the AR parameter, suggests that the RLRT for predictability has very good size properties even when the regressor has strong persistence. The Bartlett corrected RLRT achieves an O n−2 error. Power under local alternatives is obtained and extensions to more general univariate regressors and vector AR(1) regressors, where OLS may no longer be asymptotically efficient, are provided. In simulations the RLRT maintains size well, is robust to non-normal errors and has uniformly higher power than the Jansson-Moreira test with gains that can be substantial. The Campbell- Yogo Bonferroni Q test is found to have size distortions and can be significantly oversized.

  Publisher

Recent grants

• Long Memory Time Series Modelling: Computational and Statistical Efficiency, Nonstationarity/Noninvertibility and Goodness of Fit

  NSF · $116k · 2006–2010

• REML in time series models: Applications to unified inference in moderate and near integrated autoregressions, dynamic panels, cointegrated systems and non-linear IV regressions

  NSF · $143k · 2010–2014

• Fractional Cointegration, Tapering and Estimation of Misspecified Models in Long Memory Time Series

  NSF · $107k · 2003–2007

Frequent coauthors

• Rohit Deo

  New York University

  32 shared

• Clifford M. Hurvich

  16 shared

• Yi Lü

  Eye & ENT Hospital of Fudan University

  2 shared

• Yanping Yi

  Zhejiang University of Finance and Economics

  2 shared

• Califford M. Hurvich

  1 shared

Awards & honors

• Reviewer of the Year Award - 2023
• ASME DAC Best Paper Award - 2022
• Journal of Mechanical Design Editors’ Choice Honorable Menti…