Nonparametric cointegration analysis



corresponding to the r zero eigenvalues. Then:

Lemma 2. Under Assumption 3 and the conditions of Lemma 1,

         ^ï

RrTD (1) Y1 ^F1(x)2dx


Fk(1)RrτD,Z


RrM(!) ft

RM z (Fk) n

V k 7

jointly in k = 1,...,m, where the Yk ’s andZ are independent q-variate standard normally
distributed, with Y
k defined by (13). Moreover, Z does not depend on Fk .

Such weight functions Fk do exist. In particular,

Lemma 3. If Fk(x) = cos(2kπx), then the conditions (6) through (10) hold. Moreover, we then

have Fk(1) = 1, ʃʃFk(x)Fk(y)min(xy) dxdy = 1(kπ y2, ʃFk(x)2dx = 1.

There are many ways to choose these functions Fk, but as will be shown in section 5, the
above choice is optimal in some sense.

Denoting

Fk(x )2 dx


γ k =            j

y ^^I^k(x )Fk((y )min(x, y ) dxdy


, δk


Fk (1)

ʃFk (x )2 dx


(14)


it follows now easily from Lemmas 1-2:



More intriguing information

1. From Communication to Presence: Cognition, Emotions and Culture towards the Ultimate Communicative Experience. Festschrift in honor of Luigi Anolli
2. ALTERNATIVE TRADE POLICIES
3. Human Resource Management Practices and Wage Dispersion in U.S. Establishments
4. The Integration Order of Vector Autoregressive Processes
5. Whatever happened to competition in space agency procurement? The case of NASA
6. The name is absent
7. Family, social security and social insurance: General remarks and the present discussion in Germany as a case study
8. Cultural Diversity and Human Rights: a propos of a minority educational reform
9. The name is absent
10. CGE modelling of the resources boom in Indonesia and Australia using TERM