10.03.2015 Views

Economic Models - Convex Optimization

Economic Models - Convex Optimization

Economic Models - Convex Optimization

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

24 Alexis Lazaridis<br />

A straightforward approach to obtain matrices A and C, provided that<br />

some rank conditions of are satisfied, is to solve the eigenproblem (Johnston<br />

and Di Nardo, 1997, pp. 287–296).<br />

= VV −1 (2)<br />

where is the diagonal matrix of eigenvalues and V is the matrix of the<br />

corresponding eigenvectors. Note that since is not symmetric, V ̸= V −1 .<br />

Eq. (2) holds if is (n × n) and all its eigenvalues are real, which implies<br />

that the eigenvectors are real too. In cases that is defined on E n × E m ,<br />

with m>n, Eq. (2) is not applicable. If these necessary conditions hold,<br />

then from Eq. (2) follows that matrix A = V and C = V −1 . Further, the<br />

co-integrating vectors are normalized so that — usually — the first element<br />

to be equal to 1. In other words, if c i 1 (̸=0), denotes the first element1 of<br />

the ith row of matrix C, i.e., 2 c ′ i. and a j the jth column of matrix A, then<br />

the normalization process can be summarized as c ′ i. /ci 1 and a i × c i 1 , for<br />

i = 1,...,n.<br />

It is known that according to the maximum likelihood (ML) method,<br />

matrix C can be obtained by solving the constrained problem:<br />

{min det(I − C ˆ k0 ˆ −1<br />

00 ˆ 0k C ′ ) | C ˆ kk C ′ = I} (3)<br />

where matrices ˆ 00 , ˆ 0k , ˆ kk and ˆ k0 are residual co-variance matrices of<br />

specific regressions (Harris, 1995, p. 78; Johansen Juselius, 1990). These<br />

matrices appear in the last term of the concentrated likelihood of 3 Eq. (5)<br />

together with C, where is replaced by AC.<br />

Note that the minimization of Eq. (3) is with respect to the elements<br />

of matrix C. It is re-called that Eq. (3) is minimized by solving a general<br />

eigenvalue problem, i.e., finding the eigenvalues from:<br />

|λ ˆ kk − ˆ k0 ˆ −1<br />

00 ˆ 0k |=0. (4)<br />

Applying Cholesky’s factorization on the positive definite symmetric<br />

matrix ˆ −1<br />

kk , such that ˆ −1<br />

kk = LL′ ⇒ ˆ kk = (L ′ ) −1 L −1 , where L is lower<br />

1 In some computer programs, ci i is taken to be the ith element of the ith row.<br />

2 Note that dot is necessary to distinguish the jth row of C, i.e., c i. ′ , from the transposed of<br />

the jth column of this matrix (i.e., c i ′).<br />

3 Equation (5) is presented below.

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!