統計学輪講（第28回）

    統計学輪講（第28回）
    日時      2018年01月16日(火)    15時45分～16時35分
    場所      経済学部新棟３階第３教室
    講演者    伊藤　翼 (経済D2)
    演題      多変量小地域推定について

    概要
    I talk about the small area estimation in the multivariate Fay-Herriot
    model where covariance matrix of random eects are fully unknown. The 
    covariance matrix
    is estimated by a Prasad-Rao type consistent estimator, and the 
    empirical best linear un-
    biased predictor (EBLUP) of a vector of small area characteristics is 
    provided. When the
    EBLUP is measured in terms of a mean squared error matrix (MSEM), a 
    second-order ap-
    proximation of MSEM of the EBLUP and a second-order unbiased estimator 
    of the MSEM
    is derived analytically under normal case and nonparametric case in 
    closed forms. The performance is investigated through numerical
    and empirical studies.