• Title/Summary/Keyword: Mann-Kendall 검정

Search Result 48, Processing Time 0.025 seconds

A trend analysis of seasonal average temperatures over 40 years in South Korea using Mann-Kendall test and sen's slope (Mann-Kendall 비모수 검정과 Sen's slope를 이용한 최근 40년 남한지역 계절별 평균기온의 경향성 분석)

  • Jin, Dae-Hyun;Jang, Sung-Hwan;Kim, Hee-Kyung;Lee, Yung-Seop
    • The Korean Journal of Applied Statistics
    • /
    • v.34 no.3
    • /
    • pp.439-447
    • /
    • 2021
  • Due to the frequent emergence of global abnormal climates, related studies on meteorological change is being actively proceed. However, the research on trend analysis using weather data accumulated over a long period of time was insufficient. In this study, the trend of temperature time series data accumulated from automated surface observing system (ASOS) for 40 years was analyzed by using a non-parametric analysis method. As a result of the Mann-Kendall test on the annual average temperature and seasonal average temperature time series data in South Korea, it has shown that an upward trend exists. In addition, the result of calculating the Sen's slope, which can determine the degree of tendency before and after the searched change point by applying the Pettitt test, recent data after the fluctuation point confirmed that the tendency of temperature rise was even greater.

Analysis of the Secular Trend of the Annual and Monthly Precipitation Amount of South Korea (우리나라 월 및 연강수량의 경년변동 분석)

  • Kim, Gwang-Seob;Yim, Tae-Kyung;Park, Chan-Hee
    • Journal of the Korean Society of Hazard Mitigation
    • /
    • v.9 no.6
    • /
    • pp.17-30
    • /
    • 2009
  • In this study, the existence of possible deterministic longterm trend of precipitation amount, monthly maximum precipitation, rain day, the number of rain day greater than 20mm, 30mm, and 80mm was analyzed using the Mann-Kendall rank test and the data from 62 stations between 1905 and 2004 in South Korea. Results indicate that the annual and monthly rainfall amount increases and the number of rain days which have more than 80mm rainfall a day, increases. However the number of rain days decreases. Also, monthly trend analysis of precipitation amount and monthly maximum precipitation increases in Jan., May, Jun., Jul., Aug., and Sep. and they decrease in Mar., Apr., Oct., Nov., and Dec. Monthly trend of the number of rain day greater than 20mm, 30mm, and 80mm increases in Jun., Jul., Aug., and Sep. However results of Mann-Kedall test demonstrated that the ratio of stations, which have meaningful longterm trend in the significance level of 90% and 95%, is very low. It means that the random variability of the analyzed precipitation related data is much greater than their linear increment.

Trend Detection of Serially Correlated Hydrologic Series (상관성을 가진 시계열 자료의 경향성 분석에 관한 연구)

  • Oh, Je Seung;Kim, Byung Sik;Kim, Hung Soo;Seoh, Byung Ha
    • Journal of Wetlands Research
    • /
    • v.6 no.4
    • /
    • pp.35-43
    • /
    • 2004
  • The non-parametric Mann-Kendall(MK) statistical test has been widely used to assess the significance of trend in hydrologic time series. The test requires sample data should be serially independent. If sample data is serially correlated, the presence of serial correlation in a time series will affect the test ability for trend analysis. So, we would like to use the modified MK test which uses the effective sample size(ESS) to eliminate the effect of serial correlation in a series. This study investigates the ability of ESS to eliminate the influence of serial correlation of MK test by Monte Carlo simulation and by real series. As the results, MK test shows the increase of trend rate as the serial correlation is increased but the modified MK test shows ESS can eliminate the serial correlation for trend analysis. Therefore we confirmed the modified MK test is a very useful tool for trend analysis.

  • PDF

Power Test of Trend Analysis using Simulation Experiment (모의실험을 이용한 경향성 분석기법의 검정력 평가)

  • Ryu, Yongjun;Shin, Hongjoon;Kim, Sooyoung;Heo, Jun-Haeng
    • Journal of Korea Water Resources Association
    • /
    • v.46 no.3
    • /
    • pp.219-227
    • /
    • 2013
  • Time series data including change, jump, trend and periodicity generally have nonstationarity. Especially, various methods have been proposed to identify the trend about hydrological time series data. However, among various methods, evaluation about capability of each trend test has not been done a lot. Even for the same data, each method may show the different result. In this study, the simulation was performed for identification about the changes in trend analysis according to the statistical characteristics and the capability in the trend analysis. For this purpose, power test for the trend analysis is conducted using Men-Kendall test, Hotelling-Pabst test, t test and Sen test according to the slope, sample size, standard deviation and significance level. As a result, t test has higher statistical power than the others, while Mann-Kendall, Hotelling-Pabst, and Sen tests were similar results.

Analysis of Pan Evaporation Data from 1973 to 2004 in South Korea (1973년부터 2004년까지의 관측된 대형증발량 자료 분석)

  • Kim, Gwangseob;Yim, TaeKyung
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.26 no.6B
    • /
    • pp.583-596
    • /
    • 2006
  • Evaporation is an essential parameter in Global water-energy cycle and the variability of evaporation affects water resources planning and managements. In this study, the temporal variability of pan evaporation data was analyzed and trend analysis of the data using Mann-Kendall test. The relationships among evaporation and rainfall, air temperature, humidity, cloudness were analyzed. Even though the longterm trends of air temperature and rainfall increases, that of evaporation except Jinju and Yeosoo results decreases as worldwide observations. Results demonstrate that decrease of pan evaporation represents increase of terrestrial evaporation as Brutsaert and Parlange(1998)'s analysis.

A study to detect trend in serially correlated hydrological series (자료의 상관성이 경향성 분석에 미치는 영향에 대한 연구)

  • Oh Je Seung;Kim Byung Sik;Kim Hung Soo;Seoh Byung Ha
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2005.05b
    • /
    • pp.786-791
    • /
    • 2005
  • 경향성을 분석하기 위한 여러 기법 가운데 비모수적 방법인 Mann-Kendall 검정(MK 검정)은 수문시계열의 분석에서 널리 사용되어지고 있다. 이 검정 방법은 분석 대상 자료가 독립이라는 가정 하에 수행되며, 자료가 계열상관되어 있는 경우에는 그 상관성의 영향으로 경향성 존재의 유무를 정확하게 판단할 수 없게 된다. 따라서 MK 검정을 이용할 때 자료의 상관성으로 인해 받게되는 영향을 소거시키기 위해 효과적인 자료의 크기(Effective Sample Size, ESS)를 이용하는 수정된 MK 검정 방법을 이용하고자 한다. 본 연구에서는 ESS가 얼마만큼 계열상관성을 제거할 수 있는지 Monte Carlo모의를 통해 검토하였다. MK 검정 결과 계열상관계수의 증가에 따라 자료가 경향성을 나타내는 비율이 높아 겼으나, ESS에 의해 수정된 MK 검정을 수행한 결과 계열상관계수의 영향이 제거되었음을 알 수 있었다. 그러나 ESS에 치한 방법은 상관성의 영향을 과대하게 제거하게 되고, 이에 의해 실제 경향성이 존재하는 자료마저도 비 경향성이라고 판단하게 되는 오류를 가지고 있었다. 이러한 문제점을 해결하기 위해 MK 검정에서 경향성으로 판단된 자료에 대해 경향정도를 분석하여 제거한 후 다시 ESS에 의해 수정된 MK 검정을 실시하였다. 본 연구를 통하여 상관성이 존재하는 자료에 대한 MK 검정 방법의 오류를 제거 할 수 있었으며, 또한 실측 자료의 적용을 통해 수정 MK 검정이 경향성 분석에 매우 유용함을 확인 하였다.

  • PDF

Trend Analysis of Monthly Water Quality Data in Nakdong River Based on Seasonal Mann-Kendall Test (계절 Mann-Kendall 검정을 이용한 낙동강 유역의 월별 수질 장기 경향성 분석)

  • Yun, Jung-hye;Hwang, Syewoon;Kim, Dong-Hyeon;Kim, Sang-Min
    • Journal of The Korean Society of Agricultural Engineers
    • /
    • v.57 no.6
    • /
    • pp.153-162
    • /
    • 2015
  • In this study, we analyzed the trends of water quality along the main stream in Nakdong river basin using the recent data and seasonal Mann-Kendall test. Monthly averaged values of DO, BOD, SS, COD, TN, and TP from 1989 to 2014 for 14 stations (including 2 TMDLs stations) were used in the study. The trend analysis results showed that BOD and TP at most stations has decreasing temporal trend except a few stations while COD and SS showed increasing trend at most stations. Temporal trends in TN at 8 stations were found to be statistically significant and 5 of them showed increasing temporal trend. Temporally averaged BOD, COD, TN and TP were generally increasing as going downstream and the worst water quality were found at Goryeong and Hyunpung station. Overall, water quality of Nakdong river especially in COD, SS, and TN getting worse in time at most stations and as going downstream.

Characterization of Long-term Trends of Rainfall and Stream Flow in South Korea (한반도 강수량과 유량의 장기 추세 분석)

  • Kim, Gwang-Seob;Yim, Tae-Kyung
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2005.05b
    • /
    • pp.916-919
    • /
    • 2005
  • 기후변화에 따른 강수변화특성 연구는 장기 강수의 추세변화가 가용수자원과 관련된 여러 문제들과 밀접하게 연관되어 있기 때문에 중요하다. Mann-Kendall 검정을 사용하여 한반도의 월별 및 년 강수량과 유량의 추세검증분석을 수행하였다. 한반도 강우특성의 장기추세는 총강우량 증가, 총 강우일수 감소 그리고 80mm 이상 강우일수 증가로 요약될 수 있다. 강수자료의 추세분석에서는 강수량의 증가와 강우일수의 감소 그리고 호우일수의 증가를 볼 수 있었지만 MK 검정결과 $90\%$$95\%$ 유의성을 가진 증가나 감소의 추세성을 보이지는 않았다. 이는 강수량의 증가로 인한 유량의 증가 추세가 유량자체의 변동 특성보다 크지 않으므로 유량자료의 추세에서 통계적 유의성을 가지는 어떠한 경향성을 찾을 수 없음을 나타낸다.

  • PDF

Trend Analysis of the COD and Nutrients Concentrations in the Yongwon Channel, Chinhae (진해 용원수로의 COD 및 영양염류 농도 추세분석)

  • Cho, Hong-Yeon;Chae, Jang-Won;Park, Joung-Guy;Koo, Myung-Seo
    • Journal of Korean Society of Coastal and Ocean Engineers
    • /
    • v.20 no.4
    • /
    • pp.421-428
    • /
    • 2008
  • Youngwon channel located in Chinhae city and formed by the Busan New Port Construction Project has been concerned about the water quality degradation problems because of the flow and pollutants stagnation due to its long-narrow shape. In this study, the water quality(hereafter WQ) variation is analysed by using the monthly WQ data measured in Yongwon channel from 2003 to 2007. The analysis shows that the TN and TP concentration in the inside Yongwon channel is definitely worse than the TN and TP concentration in the entrance of the Yongwon channel based on the 95% confidence level. The COD, TN, and TP concentrations in the Yongwon channel are 1.34, 2.08, and 1.80 times larger than that in the entrance of the Yongwon channel, respectively. It has been found that only the TP concentration in SW-26 station has an increasing trend based on the Mann-Kendall test with respect to 95% confidence level. The other stations and the other WQ constituent changes do not have the any significant trends.

Analysis of Spatial-temporal Variability of NOAA/AVHRR NDVI in Korea (NOAA/AVHRR 정규식생지수의 시공간 변화도 분석)

  • Kim, Gwangseob;Kim, Jong Pil
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.30 no.3B
    • /
    • pp.295-303
    • /
    • 2010
  • The variability of vegetation is strongly related to the variability of hydrometeorological factors such as precipitation, temperature, runoff and so on. Analysis of the variability of vegetation will aid to understand the regional impact of climate change. Thus we analyzed the spatial-temporal variability of NOAA(National Oceanic and Atmospheric Administration)/AVHRR(Advanced Very High Resolution Radiometer) NDVI(Normalized Difference Vegetation Index). In the results from Mann-Kendall test, there is no significant linear trend of annual NDVI from 1982 to 2006 in the most area except the downward trend on the significance level 90% in the Guem-river basin area. In addition, using EOF(Empirical Orthogonal Function) analysis, the variability of NDVI in the region of higher latitude and altitude is higher than that in the other region since the spatial variability of NDVI follows the latitudinal gradient. Also we could get higher NDVI in June, July, August and September. We had the highest NDVI in Han-river basin area and the lowest in Je-Ju island.