| M. L. EATON. Multivariate Statistics: A Vector Space Approach. Wiley Series in Probability and Mathematical Statistics. John Wiley & Sons, 1983. |
....operator. If A is a r Theta n matrix, B is a s Theta p matrix and C is a t Theta q matrix, and Y is a n Theta p Theta q array, then W = A Omega B Omega C)Y = A] BY C T ] is a r Theta s Theta t array. Other uses of tensor product notation appear in multivariate models (for example, Eaton, 1983, Hocking, 1985) The Einstein summation notation (see McCullagh, 1987) could be used instead, but the operations involving orthogonal projections and transformation would be less clear. Our notation is also particularly useful in representing the third derivative of the log likelihood which ....
Eaton, M.L. (1983). Multivariate Statistics: A Vector Space Approach. John Wiley & Sons, New York.
....for the univariate normal distribution. However, we note that our statistic X 2 does not have a precise univariate analog; when p = 1 the statistic X 2 is degenerate (constant with probability one) 4 Proofs We begin our proof with two lemmas: an invariance lemma using an argument from Eaton (1983), and an approximation lemma using ideas and methods from the large sample theory of general chi squared statistics in Moore and Spruill (1975) and Pollard (1979) A projection argument then completes the proof. It is notationally convenient to prove our invariance lemma in the setting of a ....
....the special case where q = 1 and X = e. Lemma 4.1 Under the multivariate regression model described above, the standardized data Z(Y ) is ancillary and the distribution of Z(Y ) is the same for all possible choices of R(S) Proof: We shall use results and arguments from Example 7. 19 (page 292) of Eaton (1983). In this example Eaton shows that Z(Y ) is ancillary in the special case where R(S) is an upper triangular matrix with positive diagonal elements. We shall extend his argument to handle the more general matrices R(S) The matrix Z(Y ) is an element of the space F = fz : z t z = nI p and Qz ....
Eaton, M.L. (1983). Multivariate Statistics: a Vector Space Approach. Wiley, New York.
.... details of the calculations and results of computer simulations which support our theoretical analysis, we refer the reader to (Sollich, 1994) First note that, for = 0, the exact result for the average response function is Gj =0 = ff Gamma 1 Gamma 1=N ) Gamma1 for ff 1 1=N (see, e.g. Eaton, 1983), which clearly admits a series expansion in powers of 1=N . We assume that a similar expansion also exists for nonzero , and write G = G 0 G 1 =N O(1=N 2 ) 12) G 0 is the value of G in the thermodynamic limit as given by eq. 9) For finite N , the fluctuations DeltaG = G Gamma G of G ....
M L Eaton (1983). Multivariate Statistics - A Vector Space Approach. Wiley, New York.
No context found.
M. L. EATON. Multivariate Statistics: A Vector Space Approach. Wiley Series in Probability and Mathematical Statistics. John Wiley & Sons, 1983.
No context found.
Eaton, M.L. (1983). Multivariate Statistics: A Vector SpaceApproach.Wiley,New York.
No context found.
M. L. Eaton, Multivariate Statistics: A Vector Space Approach.New York: Wiley,
No context found.
M. L. Eaton, Multivariate Statistics: A Vector Space Approach, New York: Wiley, 1983.
No context found.
Eaton, M.L. (1983). Multivariate Statistics: A Vector Space Approach. Wiley, New York.
No context found.
Eaton, Morris L. (1983) Multivariate Statistics: A Vector Space Approach. Wiley, New York.
No context found.
Eaton, M. L. (1983). Multivariate Statistics: A Vector Space Approach. Wiley, New York.
No context found.
Eaton, M.L. Multivariate Statistics -- A Vector Space Approach, John Wiley & Sons, New York, 1983.
No context found.
Eaton, Morris L.:"Multivariate statistics : a vector space approach" Wiley series in probability and mathematical statistics. New York : Wiley, c1983.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC