Nonparametric cointegration analysis



4.1. The lambda-min test, and a comparison with Johansen’s tests

The results in Theorems 1-2 suggest to use the test statistic λq-rm for testing the null
hypothesis
Hr that there are r cointegrating vectors against the alternative Hr+1. We shall call
this test the lambda-min test, which (as will be shown below) is in the same spirit as
Johansen’s lambda-max test.

Johansen’s (1988) original approach is based on the following ECM of the q-variate
unit root process
zt :

p-1

z = ∏ Π∆z + γβTz  + e.,                                                  (24)

t                j t-j       1 ,     t-p         t,

j=1

where the Πj, j >0,areq×q and β and γ are q×r parameter matrices with r the number of
cointegrating vectors (the columns of
β), and the et’s are i.i.d. Nq(0,Σ) errors. By stepwise
concentrating all the parameter matrices in the likelihood function out, except the matrix
β,
Johansen shows that the ML estimator of
β can be derived from the eigenvectors of the
generalized eigenvalue problem det(
SpoSo,1Sop λSpp) = 0 = 0, where Sij = (1/n)Σn=1 Riβjτt, i,j =
o,p, with Ro,t the residual vector of the regression of zt on zt-1 ,...,zt-p+1 , and Rp,t the
residual vector of the regression of
zt-p on zt-1 ,...,zt-p+1 . Moreover, the ordered eigenvalues
λ1 .... ≥ λq involved can be used for testing hypotheses about the number of cointegrating
vectors. In particular, Johansen proposes two LR tests for the number of cointegrating vectors,
the trace test and the lambda-max test. The test statistic of the latter test, for testing
Hr
against Hr+1, is nλr+1. The trace test tests Hr against Hq, which is equivalent to the alternative
that
zt is stationary. Johansen proves that (λ1,...,λq ) converges in distribution to (c 1,...,cr
,0,...,0), where the cj,s are positive constants, and n(λr+1 ,....,λq) converges in distribution to (ε1
,...,ε
q-r), where the εj.,s are positive random variables. Comparing Johansen’s generalized
eigenvalue results with Theorems 1-2 we see that we can mimic Johansen’s tests by
transforming our generalized eigenvalues
λj,m by μj,m = 1/(n√λq+1-j,m) and replacing Johansen’s
eigenvalues in his lambda-max and trace tests by these μ
jm ’s. Then Johansen’s lambda(mu)-
max test becomes our lambda-min test. In this paper we shall focus on the lambda-min test
only, because for this test it is possible to optimize the power of the test to
m, and the order

13



More intriguing information

1. The name is absent
2. The Integration Order of Vector Autoregressive Processes
3. Investment in Next Generation Networks and the Role of Regulation: A Real Option Approach
4. Short- and long-term experience in pulmonary vein segmental ostial ablation for paroxysmal atrial fibrillation*
5. The name is absent
6. The name is absent
7. The Dictator and the Parties A Study on Policy Co-operation in Mineral Economies
8. EXECUTIVE SUMMARIES
9. Inhimillinen pääoma ja palkat Suomessa: Paluu perusmalliin
10. Stakeholder Activism, Managerial Entrenchment, and the Congruence of Interests between Shareholders and Stakeholders
11. The name is absent
12. Temporary Work in Turbulent Times: The Swedish Experience
13. Evaluating the Success of the School Commodity Food Program
14. Impact of Ethanol Production on U.S. and Regional Gasoline Prices and On the Profitability of U.S. Oil Refinery Industry
15. PROTECTING CONTRACT GROWERS OF BROILER CHICKEN INDUSTRY
16. CURRENT CHALLENGES FOR AGRICULTURAL POLICY
17. The use of formal education in Denmark 1980-1992
18. Update to a program for saving a model fit as a dataset
19. The name is absent
20. Volunteering and the Strategic Value of Ignorance