# ºtÁ¿¤½§i

### ·s»D¼ÐÃD¡G¡@( 2016-09-13 )

ºtÁ¿¥DÃD¡GTropical Storms: Changes and Trends

¥DÁ¿¤H¡GWolfgang Karl Härdle ±Ð±Â (Humboldt-Universität zu Berlin Germany)

ºtÁ¿¤é´Á¡G2016¦~9¤ë20¤é(¬P´Á¤G) 15:30 - 16:20

ºtÁ¿¦aÂI¡G(¥ú´_®Õ°Ï) ¬ì¾Ç¤@À]223«Ç

ºKn¤º®e¡G

A great deal of research in environmental and climate sciences has been dedicated to detecting change points and trends in various time series, including those related to temperature, precipitation and wind speed. The onset and end of typhoon and hurricane seasons, as well as their intensity, can change from year to year. Most environmental and climate series exhibit a pronounced annual periodicity which must be removed, or otherwise accounted for, before statements on change¡Vpoints or trends can be inferred. Motivated by the conjectured existence of trends in the intensity of tropical storms, we proposes a new inferential methodology to detect a trend in the annual pattern of environmental data. The new methodology can be applied to data which can be represented as annual curves which evolve from year to year. Other examples include annual temperature or log¡Vprecipitation curves at specific locations. Within a framework of a functional regression model, we derive two tests of significance of the slope function, which can be viewed as the slope coefficient in the regression of the annual curves on year. One of the tests relies on a Monte Carlo distribution to compute the critical values, the other is pivotal with the chi¡V square limit distribution. Practical and theoretical justification of both tests is provided and finite sample properties are investigated. Applied to tropical storm data, these tests show that there is a significant trend in the shape of the annual pattern of upper wind speed levels of hurricanes.

Keywords: change point, trend test, tropical storms, expectiles, functional data analysis¬ÛÃöÀÉ®×¡Gposter_20160920.jpg