Testing for the expected number of exceedances in strongly dependent seasonal time series

Abstract

We consider seasonal time series models with a strongly dependent residual process. The question of testing for a change in the expected number of exceedances is addressed. Based on a functional limit theorem for seasonal empirical processes, a test of the null hypothesis of no change is proposed. The method is applied to daily temperature series at various locations in Switzerland. The test reveals interesting differences in the effect of global warming on seasonal temperature exceedances.

Keywords:

• Seasonal time series
• exceedance
• long-range dependence
• empirical process
• change point

Acknowledgments

We thank MeteoSwiss for the meteorological data that have been used in the analysis in section 5. We would also like to thank the referees for their insightful comments.

Disclosure statement

No potential conflict of interest was reported by the author(s).