eduzhai > Applied Sciences > Computer Science >

Hybrid quantile estimation for asymmetric power GARCH models

  • KanKan
  • (0) Download
  • 20210425
  • Save

... pages left unread,continue reading

Document pages: 31 pages

Abstract: Asymmetric power GARCH models have been widely used to study the higher ordermoments of financial returns, while their quantile estimation has been rarelyinvestigated. This paper introduces a simple monotonic transformation on itsconditional quantile function to make the quantile regression tractable. Theasymptotic normality of the resulting quantile estimators is established undereither stationarity or non-stationarity. Moreover, based on the estimationprocedure, new tests for strict stationarity and asymmetry are alsoconstructed. This is the first try of the quantile estimation fornon-stationary ARCH-type models in the literature. The usefulness of theproposed methodology is illustrated by simulation results and real dataanalysis.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×