AKASHI, Fumiya

AKASHI, Fumiya

Name / Position

AKASHI, Fumiya / Assistant Professor

Website

Personal WebsiteOpen a new window

E-mail

akashi@e.u-tokyo.ac.jp

Curriculum Vitae

Education

March 2015 Doctor of Science, Waseda University
March 2013 Master of Science, Waseda University
March 2011 Bachelor of Engineering, Waseda University

Professional Experience

April 2019 Assistant Professor, Graduate School of Economics, University of Tokyo
April 2018 Assistant Professor, Research Institute for Science & Engineering, Waseda University
April 2017 Assistant Professor, Department of Applied Mathematics, Waseda University
April 2016 Research Associate, Department of Applied Mathematics, Waseda University
April 2015 Research Fellow-PD, Japan Society for the Promotion of Science
April 2014 Research Fellow-DC2, Japan Society for the Promotion of Science

Research Field

Mathematical statistics, Time series analysis

Research Theme

My research focuses on statistical inference for infinite variance and long-memory time series models. I am interested in robust estimation procedures based on the empirical likelihood method, self-normalization/weighting approach for nonstandard data without additional scaling of statistics or estimation of nuisance parameters. I am also working on statistical analysis of directional data, which appears in analysis of wildfire orientation or seismic data analysis.

Publications

Articles

  • Fumiya Akashi (2023). Spatial Median-Based Smoothed and Self-Weighted GEL Method for Vector Autoregressive Models. In: Liu, Y., Hirukawa, J., Kakizawa, Y. (eds) Research Papers in Statistical Inference for Time Series and Related Models. Springer, Singapore. https://doi.org/10.1007/978-981-99-0803-5_1
  • Fumiya Akashi, Masanobu Taniguchi and Yoshiyuki Tanida (2021). Estimation of linear functional of large spectral density matrix and application to Whittle’s approach. Japanese Journal of Statistics and Data Science, Volume 4, pp.449-474.
  • Fumiya Akashi, Masanobu Taniguchi and Anna Clara Monti (2020). “Robust causality test of infinite variance processes”. Journal of Econometrics. Volume 216, Issue 1, pp.235-245.
  • Fumiya Akashi, Holger Dette and Yan Liu (2018). “Change point detection in autoregressive models with no moment assumptions”. Journal of Time Series Analysis. Volume 39, pp.763-786.
  • Fumiya Akashi, Shuyang Bai and Murad S. Taqqu. (2018). “Robust regression on stationary time series: a self-normalized resampling approach”. Journal of Time Series Analysis, Volume 39, pp.417-432.
  • Fumiya Akashi, Hiroaki Odashima, Masanobu Taniguchi and Anna C. Monti (2018). “A new look at portmanteau tests”. Sankhya, Volume 80-A, Part 1, pp.121-137.
  • Fumiya Akashi (2017). “Self-weighted generalized empirical likelihood methods for hypothesis testing in infinite variance ARMA models”. Statistical Inference for Stochastic Processes. 20(3), pp.291-313.
  • Sho Shibuya, Fumiya Akashi and Taniguchi, M. (2015). “Nonparametric approach for Box-Cox transformed process”. Advances in Science, Technology and Environmentology. B12, 31-44.
  • Fumiya Akashi, Yan Liu and Masanobu Taniguchi (2015). An empirical likelihood approach for symmetric alpha-stable process. Bernoulli. 21(4), pp.2093-2119.
  • Fumiya Akashi (2014). “Empirical likelihood approach toward discriminant analysis for dynamics of stable processes”. Statistical Methodology. Volume 19, pp.25-43.
  • Fumiya Akashi (2013). “An empirical likelihood approach for discriminant analysis of non-Gaussian vector stationary linear processes”. Scientiae Mathematicae Japonicae Online. e- 2013, pp.645-660.

Books and Monographs

  • Fumiya Akashi, Masanobu Taniguchi, Anna Clara Monti and Tomoyuki Amano (2021). Diagnostic Methods in Time Series. JSS Research Series in Statistics. Springer.
  • Yan Liu, Fumiya Akashi and Masanobu Taniguchi (2018). Empirical Likelihood and Quantile Methods for Time Series: Efficiency, Robustness, Optimality and Prediction. JSS Research Series in Statistics. Springer Singapore.

Other Professional Activities and Awards

Other Professional Activities and Services - Grants

  • Apr. 2020 - Mar. 2024
    JSPS Grant-in-Aid for Young Scientists “Statistical inference for nonstandard data via time varying processes, robust regression and directional statistics”
  • Apr. 2016 - Mar. 2020
    JSPS Grant-in-Aid for Young Scientists (B) “Robust nonparametric inference for infinite variance processes with self-normalized empirical likelihood methods”
  • Apr. 2014 - Mar. 2016
    Grant-in-Aid for JSPS Research Fellow “Empirical likelihood approach to discriminant analysis of infinite variance time series models”

Awards

  • 2023, JSS Ogawa Award, Japan Statistical Society