Bootstrap testing for fractional integration

• Asymptotic tests for fractional integration, such as the Geweke-Porter-Hudak test, the modified rescaled range test and Lagrange multiplier type tests, exhibit size distortions in small samples. This paper investigates a parametric bootstrap testing procedure, for size correction, by means of a computer simulation study. The bootstrap provides a practical method to eliminate size distortions in the case of an asymptotic pivotal statistic while the power, in general, is close to the corresponding size adjusted asymptotic test. The results are very encouraging and suggest that a bootstrap testing procedure does correct for size distortions.

Subject headings

NATURVETENSKAP  -- Matematik -- Sannolikhetsteori och statistik (hsv//swe)

NATURAL SCIENCES  -- Mathematics -- Probability Theory and Statistics (hsv//eng)

Publication and Content Type

ovr (subject category)

vet (subject category)