Performance of the Standard Normal Homogeneity Test for the homogenization of mean seasonal snow depth time series

2017 ◽  
Vol 37 ◽  
pp. 1267-1277 ◽  
Author(s):  
Giorgia Marcolini ◽  
Alberto Bellin ◽  
Gabriele Chiogna
Keyword(s):  
Time Series ◽  
Snow Depth ◽  
Homogeneity Test ◽  
Seasonal Snow ◽  
Standard Normal Homogeneity Test ◽  
Standard Normal

scholarly journals A Novel Approach for the Detection of Inhomogeneities Affecting Climate Time Series

2012 ◽  
Vol 51 (2) ◽  
pp. 317-326 ◽  
Author(s):  
Andrea Toreti ◽  
Franz G. Kuglitsch ◽  
Elena Xoplaki ◽  
Jürg Luterbacher
Keyword(s):  
Time Series ◽  
Markov Models ◽  
Winter Precipitation ◽  
Homogeneity Test ◽  
Temperature And Precipitation ◽  
Novel Approach ◽  
Standard Normal Homogeneity Test ◽  
Standard Normal ◽  
Set Up ◽  
Climate Time Series

AbstractSudden changes caused by nonclimatic factors (inhomogeneities) usually affect instrumental time series of climate variables. To perform robust climate analyses based on observations, a proper identification of such changes is necessary. Here, an approach (named the “GAHMDI” method, after its components and purpose) that is based on a genetic algorithm and hidden Markov models is proposed for detection of inhomogeneities caused by changes in the mean and variance. Simulated series and a case study (winter precipitation from a weather station located in Milan, Italy) are set up to compare GAHMDI with existing methodologies and to highlight its features. For the identification of a single changepoint, GAHMDI performs similarly to other methods (e.g., standard normal homogeneity test). However, for the identification of multiple inhomogeneities and changes in variance, GAHMDI returns better results than three widespread methods by avoiding overdetection. For future applications and research in the homogenization of climate datasets (temperature and precipitation) the use of GAHMDI is encouraged, preferably in combination with another detection procedure (e.g., the method of Caussinus and Mestre) when metadata are not available. Since GAHMDI is developed in the generic context of time series segmentation, it can be applied to series of generic variables—for instance, those related to economics, biology, and informatics.

scholarly journals Penalized Maximal t Test for Detecting Undocumented Mean Change in Climate Data Series

2007 ◽  
Vol 46 (6) ◽  
pp. 916-931 ◽  
Author(s):  
Xiaolan L. Wang ◽  
Qiuzi H. Wen ◽  
Yuehua Wu
Keyword(s):  
Time Series ◽  
Practical Importance ◽  
T Test ◽  
Data Series ◽  
Homogeneity Test ◽  
Climate Data ◽  
Series Length ◽  
Standard Normal Homogeneity Test ◽  
Higher Power ◽  
Standard Normal

Abstract In this paper, a penalized maximal t test (PMT) is proposed for detecting undocumented mean shifts in climate data series. PMT takes the relative position of each candidate changepoint into account, to diminish the effect of unequal sample sizes on the power of detection. Monte Carlo simulation studies are conducted to evaluate the performance of PMT, in comparison with the most popularly used method, the standard normal homogeneity test (SNHT). An application of the two methods to atmospheric pressure series recorded at a Canadian site is also presented. It is shown that the false-alarm rate of PMT is very close to the specified level of significance and is evenly distributed across all candidate changepoints, whereas that of SNHT can be up to 10 times the specified level for points near the ends of series and much lower for the middle points. In comparison with SNHT, therefore, PMT has higher power for detecting all changepoints that are not too close to the ends of series and lower power for detecting changepoints that are near the ends of series. On average, however, PMT has significantly higher power of detection. The smaller the shift magnitude Δ is relative to the noise standard deviation σ, the greater is the improvement of PMT over SNHT. The improvement in hit rate can be as much as 14%–25% for detecting small shifts (Δ < σ) regardless of time series length and up to 5% for detecting medium shifts (Δ = σ–1.5σ) in time series of length N < 100. For all detectable shift sizes, the largest improvement is always obtained when N < 100, which is of great practical importance, because most annual climate data series are of length N < 100.

scholarly journals Mudança no Regime Temporal da Temperatura do Ar e Precipitação Pluviométrica na Região de Rio Largo, Alagoas (Change in the Temporal Regime of Air Temperature and Rainfall in the Region of Rio Largo, Alagoas, Brazil)

2014 ◽  
Vol 7 (4) ◽  
pp. 662
Author(s):  
Henderson Silva Wanderley ◽  
André Luiz de Carvalho ◽  
Ronabson Cardoso Fernandes ◽  
José Leonaldo de Souza
Keyword(s):  
Time Series ◽  
Air Temperature ◽  
Change Point ◽  
Statistical Tests ◽  
Linear Regression Analysis ◽  
Homogeneity Test ◽  
Significance Level ◽  
Standard Normal Homogeneity Test ◽  
Standard Normal ◽  
History Of

Compreender como as alterações no clima têm modificado a temperatura do ar e a precipitação pluvial de uma região é essencial, sobretudo para regiões como o Nordeste brasileiro, que apresentam vasto histórico de secas e altas temperaturas. No entanto, estudos com esse fim são escassos ou até mesmo inexistentes para essa região. Deste modo, objetivou-se identificar mudanças ocorridas no regime temporal da temperatura diurna e noturna e na precipitação na região de Rio Largo, Alagoas. Para isto, utilizaram-se dados de temperatura diurna (máxima) e noturna (mínima) compreendidos entre 1973 e 2002, e de precipitação dispostos entre 1973 e 2008. As séries temporais foram submetidas ao teste estatístico SNHT (Standard Normal Homogeneity Test) para identificar possíveis pontos de mudança na média. A análise de regressão linear simples foi utilizada para identificar alterações nas séries temporais, testada por meio do teste t de Student, adotando-se nível de significância estatística de 0,05%, para ambos os testes estatísticos. A análise mostrou que as temperaturas demostraram pontos de mudanças significativos, no entanto, foi observada uma defasagem de quase dez anos entre os pontos. A tendência identificada entre as temperaturas foram opostas entre si, sendo de aumento para a temperatura diurna e de redução para a noturna. A precipitação demostrou tendência de redução, no entanto, não apresentou mudança estatística significativa.  ABSTRACTUnderstanding how changes in climate have changed air temperature and rainfall in a region is essential, especially for regions such as the Brazilian Northeast, which have long history of drought and high temperatures. However, studies for this purpose are scarce or even nonexistent for this region. Thus, this study aimed to identify changes in the temporal regime of daytime and nighttime temperature and rainfall in the region of Rio Largo, Alagoas, Brazil. For this, it was used data of daytime temperature (maximum) and night (minimum) ranging from 1973 to 2002, and rainfall arranged between 1973 and 2008. Time series were submitted to SNHT (Standard Normal Homogeneity Test) statistical test to identify possible change point in average. A simple linear regression analysis was used to identify changes in time series, tested using the Student t test, adopting a significance level of 0.05%, for both statistical tests. The analysis showed that temperatures demonstrated significant change points, however, there was a gap of almost ten years between the points. The trend identified among the temperatures was opposed to each other, with increasing daytime temperature and reduction of nighttime temperature. Rainfall demonstrated trend of reducing, however, showed no statistically significant change.Keywords: daytime and nighttime temperature, SNHT, trend, change point. 

A note on the use of the standard normal homogeneity test to detect inhomogeneities in climatic time series

2011 ◽  
Vol 31 (4) ◽  
pp. 630-632 ◽  
Author(s):  
A. Toreti ◽  
F. G. Kuglitsch ◽  
E. Xoplaki ◽  
P. M. Della-Marta ◽  
E. Aguilar ◽  
...  
Keyword(s):  
Time Series ◽  
Homogeneity Test ◽  
Standard Normal Homogeneity Test ◽  
Standard Normal ◽  
Climatic Time Series

scholarly journals The Ås Temperature Series in Southern Norway–Homogeneity Testing And Climate Analysis

2014 ◽  
Vol 7 (1) ◽  
pp. 7-26 ◽  
Author(s):  
Herdis M. Gjelten ◽  
Øyvind Nordli ◽  
Arne A. Grimenes ◽  
Elin Lundstad
Keyword(s):  
Time Series ◽  
Temperature Series ◽  
Homogeneity Test ◽  
Linear Temperature ◽  
Homogeneity Testing ◽  
Standard Normal Homogeneity Test ◽  
Standard Normal ◽  
Southern Norway ◽  
Climate Analysis

Abstract Homogeneity is important when analyzing climatic long-term time series. This is to ensure that the variability in the time series is not affected by changes such as station relocations, instrumentation changes and changes in the surroundings. The subject of this study is a long-term temperature series from the Norwegian University of Life Sciences at Ås in Southern Norway, located in a rural area about 30 km south of Oslo. Different methods for calculation of monthly mean temperature were studied and new monthly means were calculated before the homogeneity testing was performed. The statistical method used for the testing was the Standard Normal Homogeneity Test (SNHT) by Hans Alexandersson. Five breaks caused by relocations and changes in instrumentation were identified. The seasonal adjustments of the breaks lay between -0.4°C and +0.5°C. Comparison with two other homogenized temperature series in the Oslo fjord region showed similar linear trends, which suggests that the long-term linear temperature trends in the Oslo fjord region are not much affected by spatial climate variation.

The Application of the Smirnov Test in the Homogeneity Test for Non-Normal Distribution Temperature Series

2012 ◽  
Vol 516-517 ◽  
pp. 530-535
Author(s):  
Xin Jie Deng ◽  
Yang Sheng You ◽  
Yan Ying Chen ◽  
Xue Mei Yang
Keyword(s):  
Normal Distribution ◽  
Classical Method ◽  
Temperature Series ◽  
Homogeneity Test ◽  
Test Results ◽  
Standard Normal Homogeneity Test ◽  
Standard Normal ◽  
Better Than ◽  
Smirnov Test

The homogeneity test is the first stage to revise the climate records. Its accuracy will directly affect the follow-up work. The classic method SNHT (Standard Normal Homogeneity Test) can only be applied in climatic sequences obey normal distribution, but lots of non-normality climate sequences need to be examined. In this paper, the Smirnov Test was introduced to test the homogeneity of the temperature series, which is a classical method for distribution test, and it can apply for the temperature sequences obey any distribution. The homogeneity test results by testing Chongqing Municipality's temperature sequences show that: the Smirnov Test is better than SNHT

scholarly journals Efficiencies of Inhomogeneity-Detection Algorithms: Comparison of Different Detection Methods and Efficiency Measures

2013 ◽  
Vol 2013 ◽  
pp. 1-15 ◽  
Author(s):  
Peter Domonkos
Keyword(s):  
Linear Trend ◽  
Change Point Detection ◽  
Detection Methods ◽  
Homogeneity Test ◽  
Detection Algorithms ◽  
Efficiency Measures ◽  
Standard Normal Homogeneity Test ◽  
Standard Normal ◽  
The Difference ◽  
Homogenization Methods

Efficiency evaluations for change point Detection methods used in nine major Objective Homogenization Methods (DOHMs) are presented. The evaluations are conducted using ten different simulated datasets and four efficiency measures: detection skill, skill of linear trend estimation, sum of squared error, and a combined efficiency measure. Test datasets applied have a diverse set of inhomogeneity (IH) characteristics and include one dataset that is similar to the monthly benchmark temperature dataset of the European benchmarking effort known by the acronym COST HOME. The performance of DOHMs is highly dependent on the characteristics of test datasets and efficiency measures. Measures of skills differ markedly according to the frequency and mean duration of inhomogeneities and vary with the ratio of IH-magnitudes and background noise. The study focuses on cases when high quality relative time series (i.e., the difference between a candidate and reference series) can be created, but the frequency and intensity of inhomogeneities are high. Results show that in these cases the Caussinus-Mestre method is the most effective, although appreciably good results can also be achieved by the use of several other DOHMs, such as the Multiple Analysis of Series for Homogenisation, Bayes method, Multiple Linear Regression, and the Standard Normal Homogeneity Test.

Sign in / Sign up

Export Citation Format

Share Document