Brown-Forsythe based method for detectingchange points in hydrological time series
Received date: 2004-11-05
Revised date: 2005-03-22
Online published: 2005-10-15
The dramatic change of hydrological cycle and natural condition and the increasing intensity of human activity usually result in the step trend of streamflow. Change point detection in streamflow series is an important way to understand and diagnose the step trend. Up to now, many methods have been developed to detect the change point, among which the one derived from basic statistics theory is most widely used for its simplicity, but is also limited for its much assumption for data at the same time. In terms of theory of analysis of variance, a detection method based on Brown-Forsythe test is proposed in this paper, which retains the virtue of simplicity and loose the limitation for data. The method based on Brown-Forsythe test is used in change point detection of Kaidu streamflow of Xinjiang which indicates that 1973 and 1986 are two change points. However, other traditional methods take 1990 as the second change point. Which is true? On the one hand, Kaidu river is mainly influenced by climate, especially precipitation and some researches have indicated that the characteri stics of climate and hydrology of Xinjiang changed acutely in 1973 and 1987. On the other hand, taking 1986 as a change point will make not only the level diff erence between separated series but also the step between change point and next year more significant than in 1990. So it is reasonable to make 1973 and 1986 as the real change points and the method based on Brown-Forsythe test is suitable for hydrological time series. The normality and randomness violation of Kaidu streamflow data is probably the main reason for traditional method to get false results. In the future, the research about change point detection will still be focused on improving the sturdiness of methods for skew data.
Key words： Brown-Forsythe test; change points; hydrological time series
ZHANG Yi-chi, ZHOU Cheng-hu, LI Bao-lin . Brown-Forsythe based method for detectingchange points in hydrological time series[J]. GEOGRAPHICAL RESEARCH, 2005 , 24(5) : 741 -748 . DOI: 10.11821/yj2005050011
[1] Hirsch R M,Alexander R B,Smit h R A. Selection of met hods for t he detection and estimation of t rends in waterqualit y. Water Resources Research,1991,27(5):803～813.
[2] Z X Xu,K Takeuchi,H Ishidaira1 Long-term t rends of annual time temperat ure and precipitation time series in J apan. Journal of Hydroscience and Hydraulic Engineering,2002,20(2):11～26.
[3] Gregory J McCabe1 A step increase in st reamflow in t he conterminous United States.Geop hysical Research Letters,2002,29(24):1～4.
[4] 海米提·依米提,塔西甫拉提·特依拜,熊黑钢.内流河流域水资源利用对径流年际年内变化影响的分析2以塔里木河流域为例.地理研究,2000,19(3):271～276.
[5] 吴凯,唐登银,谢贤群.黄河下游河川径流的变化趋势与对策.地理研究,2000,19(4):377～382.
[6] 郝芳华,杨桂莲,吴险峰,等.黄河小花间石山林区产汇流特征.地理研究,2004,23(2):165～174.
[7] Lee A F S,Heghinian S M1 A shift of t he mean level in a sequence of independent normal rando m variable:A Bayeaian Approach. Technometrics,1977,19(4):503～506.
[8] Pettitt A N1 A non2paramet ric app roach to t he change2point p roblem1 Applied Statistics,1979,28(2):126～135.
[9] Pettitt A N1 Some result s on estimating a change2point using non2paramet ric t ype statistics. Journal of StatisticalCo mp utation and Simulation,1980,11:261～272.
[10] Pierre Ozer,Michel Erpicum,Gaston Demaree,et al1 The Sahelian drought may have ended during t he 1990s.Hydrological Sciences Journal,2003,48(3):489～496.
[11] Yannl’Hote,Gil Mahe,Bonavent ure SOMé. Reply to“The Sahelian drought may have ended during t he 1990s”.Hydrological Sciences Journal,2003,48(3).
[12] 丁晶.洪水时间序列干扰点的统计推断.武汉水利水电学院学报,1986,(5).
[13] 丁晶,邓育仁.随机水文学.成都:成都科技大学出版社,1988. 65～92.
[14] 夏军.灰色系统水文学理论、方法及应用.武汉:华中理工大学出版社,1998,225～240.
[15] 夏军,穆宏强,邱训平,等.水文序列的时间变异性分析.长江职工大学学报,2001,18(3):1～4.
[16] 肖宜,夏军,申明亮,等.差异信息理论在水文时间序列变异点诊断中的应用.中国农村水利水电,2001,(11):28～30.
[17] 王孝礼,胡宝清,夏军.水文时序趋势与变异点的R/S分析法.武汉大学学报(工学版),2002,35(2):10～12.
[18] 宋立松.曹娥江低潮位序列突变成份分析.泥沙研究,2000,(1):69～72.
[19] 马振华,等.现代应用数学手册-概率统计与随机过程卷.北京:清华大学出版社,20021 276～285.
[20] Brown M B,Forsyt he A B1 The small sample behavior of some statistics which test t he equalit y of several means.Techno met rics,1974,16(1):129～132.
[21] Brown M B,Forsyt he A B. The ANOVA and multiple co mparisons for data wit h heterogeneous variances1 Biomet rics,1974,(30):719～7241
[22] 吴素芬.新疆河流径流量三十余年来的变化.干旱区地理,1995,18(2):36～41.
[23] 李燕.近40a来新疆河流洪水变化.冰川冻土,2003,25(3):342～346.
[24] 江剑民,刘荣.对我国年、季大气干旱指数的气候跃变分析.气象学报,1993,51(2):237～240.
[25] 施雅风,沈永平,胡汝骥.西北气候由暖干向暖湿转型的信号、影响和前景初步探讨.冰川冻土,2002,24(3):219～225.
[26] 施雅风,沈永平,李栋梁,等.中国西北气候由暖干向暖湿转型的特征和趋势探讨.第四纪研究,2003,23(2):152～1641
[27] 胡汝骥,姜逢清,王亚俊,等.新疆气候由暖干向暖湿转变的信号及影响.干旱区地理,2002,25(3):194～200.
[28] 张国威,吴素芬,王志杰.西北气候环境转型信号在新疆河川径流变化中的反映.冰川冻土,2003,25(2):183～187.
/
| 〈 |
|
〉 |