TY - JOUR

T1 - Uniform approximations for distributions of continuous random variables with application in dual STATIS method.

AU - Ramos, Luís Pedro Carneiro

AU - Lita da Silva, João Filipe

PY - 2014/1/1

Y1 - 2014/1/1

N2 - The matrix S = [tr(W(i)QW(j)Q)] (i) ,(j=1) (,...,) (k) where Q is a symmetric positive definite matrix and W-i = X-i'DiXi, i = 1,..., k is formed by data tables X-i and diagonal matrices of weights D-i, plays a central role in dual STATIS method. In this paper, we approximate the distribution function of the entries of S, assuming data tables X-i given by U-i + E-i, i = 1,..., k with independent random matrices E-i representing errors, in order to obtain (approximately) the distribution of Sv, where v is the orthonormal eigenvector of S associated to the largest eigenvalue. To achieve this goal, we approximate uniformly the distribution of each entry of S. In general, our technique consists in to approximate uniformly the distribution sequence {g(V-n + mu(n)), n >= 1}, where g is some smooth function of several variables, {V-n, n >= 1} is a sequence of identically distributed random vectors of continuous type and {mu(n)} is a non-random vector sequence.

AB - The matrix S = [tr(W(i)QW(j)Q)] (i) ,(j=1) (,...,) (k) where Q is a symmetric positive definite matrix and W-i = X-i'DiXi, i = 1,..., k is formed by data tables X-i and diagonal matrices of weights D-i, plays a central role in dual STATIS method. In this paper, we approximate the distribution function of the entries of S, assuming data tables X-i given by U-i + E-i, i = 1,..., k with independent random matrices E-i representing errors, in order to obtain (approximately) the distribution of Sv, where v is the orthonormal eigenvector of S associated to the largest eigenvalue. To achieve this goal, we approximate uniformly the distribution of each entry of S. In general, our technique consists in to approximate uniformly the distribution sequence {g(V-n + mu(n)), n >= 1}, where g is some smooth function of several variables, {V-n, n >= 1} is a sequence of identically distributed random vectors of continuous type and {mu(n)} is a non-random vector sequence.

KW - uniform approximations

KW - dual STATIS method

M3 - Article

SN - 1645-6726

VL - 12

SP - 101

EP - 118

JO - REVSTAT: Statistical Journal

JF - REVSTAT: Statistical Journal

IS - 2

ER -