Research

Research Interests

Functional time series and high-dimensional time series

Nonparametric methods and dynamic factor models

Big data with temporal dependence

Statistical applications in science, engineering and business

Publications & Preprints

  1. Liu, X., and Zhang, T. Factor analysis for high-dimensional time series with change point. (under review).
  2. Liu, X., and Chen, R. Threshold factor models for high-dimensional time series. Journal of Econometrics (under review).
  3. Liu, X., and Chen, E. Helping effects against curse of dimensionality in threshold factor models for matrix time series. (under review).
  4. Zheng, C., Sundaramurth, C., Liu, X. Non-profits for Profit? Exploring the Triggers and Enabling Factors Associated with Engaging in Entrepreneurial Changes. International Journal of Entrepreneurship and Innovation (under review).
  5. Wang, D., Liu, X, and Chen, R.(2018). Factor models for matrix-valued high-dimensional time series. Journal of Econometrics, 208(1), 231-248.
  6. Liu, X., Xiao, H., and Chen, R. (2016). Convolutional autoregressive models for functional time series. Journal of Econometrics, 194(2), 263-282.
  7. Liu, X. and Chen, R. (2016). Regime-switching factor models for high-dimensional time series and Supplement, Statistica Sinica, 26(4), 1427-1451.
  8. Liu, X., Cai, Z., and Chen, R. (2015). Functional coefficient seasonal time series models with an application of Hawaii tourism data. Computational Statistics, 30(3), 719-744.


Software:

R package NTS: Simulation, estimation, prediction procedure, and model identification methods for nonlinear time series analysis, including threshold autoregressive models, Markov-switching models, convolutional functional autoregressive models, nonlinearity tests, Kalman filters and various sequential Monte Carlo methods.

Selected Conferences & Presentations

  • Threshold Factor Models for High-Dimensional Time Series, invited talk given at the 3rd International Conference on Econometrics and Statistics, Taichung, Taiwan, June 2019.
  • Factor Models for Matrix-valued Time Series, invited talk given at the 2019 ICSA Applied Statistics Symposium, Raleigh, North Carolina, June 2019.
  • Helping Effect in Threshold Factor Models for High-Dimensional Time Series, invited talk given at the 2019 ICSA Conference on Data Sciences, Xishuangbanna, Yunnan, January 2019.
  • New Methods for Threshold Variable Identification and Estimation in Threshold Dynamic Factor Models, talk given at Joint Statistical Meetings, Vancouver, Canada, July 2018.
  • Threshold Factor Models for High-Dimensional Time Series, invited talk given at the 2018 ICSA Applied Statistics Symposium, New Brunswick, New Jersey, June 2018.
  • Estimation of Correlation Matrix with Block Structure, talk given at 2017 Joint Statistical Meetings, Baltimore, Maryland, August 2017.
  • Threshold Factor Models for High-Dimensional Time Series, invited talk given at 2017 IMS-China International Conference on Statistics and Probability, Nanning, Guangxi, China, July 2017.
  • Threshold Factor Models for High-Dimensional Time Series, invited talk given at UCSD, San Diego, California, November 2016.
  • Prediction and Interpretation of Hawaii Tourism Data, paper presented at INFORMS conference on Business Analytics \& Operations Research, Orlando, Florida, April 2016.
  • Convolutional Functional Autoregressive Models, invited talk given at University of Miami, Management Science Department, Miami, Florida, November 2015.
  • New Models and Methods for Time Series, invited talk given at San Diego State University, Department of Mathematics and Statistics, San Diego, California, September 2015.
  • Convolutional Autoregressive Models: Prediction and Inference, talk given at Joint Statistical Meetings, Seattle, Washington, August 2015.
  • Convolutional Autoregressive Models for Functional Time Series with an Application of Implied Volatility Curves, invited talk given at the Fifth international IMS-FIPS workshop, New Brunswick, New Jersey, June 2015.
  • Convolutional Autoregressive Models for Functional Time Series, invited paper presented at NSF workshop for Empirical Process and Modern Statistical Decision Theory, Yale University, New Haven, Connecticut, May 2015.
  • Convolutional Autoregressive Models for Functional Time Series, invited talk given at The University of Kansas, Lawrence, Kansas, May 2015.
  • Convolutional Functional Autoregressive Models for Functional Time Series and Their Applications, invited paper presented at Deming Conference, Atlantic City, New Jersey, December 2014.
  • Regime-Switching Factor Models for High-Dimensional Time Series, invited talk given at Guanghua Time Series Forum, Guanghua School of Management, Peking University, Beijing, China, August 2014.
  • Convolutional Autoregressive Models for Functional Time Series, invited talk given at Mathematical Science Center, Tsinghua University, Beijing, China, July 2014.