A Note on the Properties of Power-Transformed Returns in Long-Memory Stochastic Volatility Models with Leverage Effect Articles uri icon

publication date

  • August 2009

start page

  • 3593

end page

  • 3600


  • 10


  • 53

International Standard Serial Number (ISSN)

  • 0167-9473

Electronic International Standard Serial Number (EISSN)

  • 1872-7352


  • According to the Taylor-Effect the autocorrelations of absolute financial returns are larger than the ones of squared returns. In this work, we analyze in detail, for two different asymmetric stochastic volatility models, how the Taylor-Effect relates to the most important model characteristics: the asymmetry, the volatility persistence and the kurtosis. We also realize Monte Carlo experiments to infer about possible biases of the sample Taylor-Effect and we fit the models to the return series of the Dow Jones