Abstract
Asymptotic tests for fractional integration are usually badly sized in small samples, even for normally distributed processes. Furthermore, tests that are well-sized (under normality) may be seriously distorted by non-normalities and ARCH errors. This paper demonstrates how the bootstrap can be implemented to correct for such size distortions. It is shown that a well-designed bootstrap test based on the MRR and GPH tests is exact, and that a procedure based on the REG test is nearly exact. Ort, förlag, år, upplaga, sidor