991
Views
1
CrossRef citations to date
0
Altmetric
Articles

Bootstrap Inference in Cointegrating Regressions: Traditional and Self-Normalized Test Statistics

ORCID Icon &

Figures & data

Table 1 Empirical sizes of the tests for H0: β1=1, β2=1 at 5% level based on asymptotic critical values.

Table 2 Empirical sizes of the tests for H0: β1=1, β2=1 at 5% level based on bootstrap critical values.

Fig. 1 Asymptotic power of the traditional and self-normalized Wald-type tests for H0: β=β0 at the nominal 5% level under local alternatives β=β0+c T1. Note: The power curves for τD(Ω̂u·v) and τFM(Ω̂u·v) coincide.

Fig. 1 Asymptotic power of the traditional and self-normalized Wald-type tests for H0: β=β0 at the nominal 5% level under local alternatives β=β0+c T−1. Note: The power curves for τD(Ω̂u·v) and τFM(Ω̂u·v) coincide.

Fig. 2 Size-corrected power of the tests for H0: β1=1, β2=1 at 5% level based on asymptotic critical values (top row) and bootstrap critical values (bottom row) for T = 100 and ϕ=0.3. Note: Long-run variance parameters are estimated using the Bartlett kernel and the VAR sieve bootstrap is based on AIC.

Fig. 2 Size-corrected power of the tests for H0: β1=1, β2=1 at 5% level based on asymptotic critical values (top row) and bootstrap critical values (bottom row) for T = 100 and ϕ=0.3. Note: Long-run variance parameters are estimated using the Bartlett kernel and the VAR sieve bootstrap is based on AIC.

Table 3 Realizations of test statistics for H0: β=1.

Supplemental material

JBES-P-2022-0187_Revision2_Unblinded_OnlineAppendix.pdf

Download PDF (651.2 KB)

Data Availability Statement

MATLAB code for empirical applications is available on www.github.com/kreichold/CointSelfNorm