• 中文版
  • English
Home
  • About Us
    • History
    • 10th Anniversary
    • 20th Anniversary
    • 30th Anniversary
  • People
    • Faculty
    • Staff
    • Postdoc
    • R.A.
    • Student
    • Advisory Board
    • Visiting Scholar
    • Past Faculty
  • Location Academia Sinica
    • Home
    • About Us
      • History
      • 10th Anniversary
      • 20th Anniversary
      • 30th Anniversary
    • People
      • Faculty
      • Staff
      • Postdoc
      • Research Assistant
      • Student
      • Advisory Board
      • Visiting Scholar
      • Past Faculty
    • Statistica Sinica
    • Seminar
    • Research Groups
    • Library
    • Computer Center
    • Cooperation Center
    • Events
    • Recruiting
    • Announcements
    • Other Links
      • Intranet
      • Web Resource
      • Site Map
    • Location
    • Academia Sinica
    • 中文版

    Statistica Sinica

    Seminar

    Research Groups

    Library

    Computer Center

    Cooperation Center

    Events

    Recruiting

    Announcements


    Other Links

    • Intranet
    • Web Resource
    • Site Map

    Seminars

    Covariance Matrix Estimation in Random Effect Models Using Metropolis Stochastic Approximation Methods with Data-driven Proposals
    2017 Dec 04 (Mon), 10:30 AM
    中研院-統計所 2F 交誼廳
    茶 會:上午10:10統計所二樓交誼廳
    Asst. Prof. Tso-Jung Yen (顏佐榕 助研究員)
    中央研究院 統計科學研究所
     

    Abstract

        In this paper we propose a method for estimating the covariance matrix of random effects in mixed effect models. We adopt a stochastic approach to approximating the gradient of the log marginal likelihood function. This approach uses a Metropolis-Hastings algorithm to sample random effects from distributions conditional on observed information. In particular, to make the algorithm efficient, this approach uses a data-driven proposal for sampling random effects from target distributions. As a result of that, this approach can achieve high accuracy in approximating the log marginal likelihood. We apply the approach to estimate the covariance matrix of the random effects in various models, including generalized linear mixed models and the Gaussian graphical model.


    128 Academia Road, Section 2, Nankang, Taipei 11529, Taiwan

    TEL: +886-2-2783-5611   FAX: +886-2-2783-1523

    2016 © Institute of Statistical Science, Academia Sinica   【Security & Privacy】

    128 Academia Road, Section 2, Nankang, Taipei 11529, Taiwan

    TEL: +886-2-2783-5611
    FAX: +886-2-2783-1523

    2016 © Institute of Statistical Science, Academia Sinica
    【Security & Privacy】