Rank-Sum Tests for Dispersions

Ansari, Abdur Rahman; Bradley, Ralph A.

doi:10.1214/aoms/1177705688

Cited by 308 publications

(129 citation statements)

References 8 publications

Supporting

Mentioning

125

Contrasting

Unclassified

Order By: Relevance

“…• The nonparametric Wilcoxon rank sum test (Ansari and Bradley 1960) allows assessing the bias between two series. For two given samples, the difference between the data are calculated and classified in ascending order of the absolute value of the differences.…”

Section: Methodsmentioning

confidence: 99%

Characterization of the rainy season in Burkina Faso and it’s representation by regional climate models

et al. 2012

View full text Add to dashboard Cite

West African monsoon is one of the most challenging climate components to model. Five regional climate models (RCMs) were run over the West African region with two lateral boundary conditions, ERA-Interim re-analysis and simulations from two general circulation models (GCMs). Two sets of daily rainfall data were generated from these boundary conditions. These simulated rainfall data are analyzed here in comparison to daily rainfall data collected over a network of ten synoptic stations in Burkina Faso from 1990 to 2004. The analyses are based on a description of the rainy season throughout a number of it's characteristics. It was found that the two sets of rainfall data produced with the two driving data present significant biases. The RCMs generally produce too frequent low rainfall values (between 0.1 and 5 mm/ day) and too high extreme rainfalls (more than twice the observed values). The high frequency of low rainfall events in the RCMs induces shorter dry spells at the rainfall thresholds of 0.1-1 mm/day. Altogether, there are large disagreements between the models on the simulate season duration and the annual rainfall amounts but most striking are their differences in representing the distribution of rainfall intensity. It is remarkable that these conclusions are valid whether the RCMs are driven by re-analysis or GCMs. In none of the analyzed rainy season characteristics, a significant improvement of their representation can be found when the RCM is forced by the re-analysis, indicating that these deficiencies are intrinsic to the models.

show abstract

Section: Methodsmentioning

confidence: 99%

Characterization of the rainy season in Burkina Faso and it’s representation by regional climate models

et al. 2012

View full text Add to dashboard Cite

show abstract

“…The Ansari-Bradley test corresponds to the scale model Being a Wald test, the asymptotic distribution of W is 1 2 , while its exact distribution is not obvious. However, W is a one to one function of F, and so the two test are equivalent.…”

Section: Lepage Test (L)mentioning

confidence: 99%

“…We call the test based on R the R Test. In large samples the denominator in R will approximate 1 2 − 2 2 and R will have asymptotic distribution 1 2 .…”

Section: Lepage Test (L)mentioning

confidence: 99%

“…Procedures proposed by Kamat (1956) and Rosenbaum (1953) seem likely to lack power. Ansari and Bradley (1960) developed a rank test for dispersion. They have shown the equivalence of two rank tests for comparing dispersion, one test due to Barton and David (1958), the other to Ansari and Freund, and have provided tables of the exact distribution.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performance of Two Sample Scale Tests: An Empirical Study

Gogoi¹,

Gogoi²

2016

International Advanced Research Journal in Science, Engineering

View full text Add to dashboard Cite

“…Other ranking schemes for testing against dispersion have been suggested -notably by Ansari and Bradley [2]. These tests have however been shown to be equivalent [10].…”

Section: Rank Statistics and Pixelsmentioning

confidence: 99%

Variance Ranklets: orientation–selective rank features for contrast modulations

Azzopardi¹,

Smeraldi²

2009

Procedings of the British Machine Vision Conference 2009

View full text Add to dashboard Cite

We introduce a novel type of orientation-selective rank features that are sensitive to contrast modulations (second-order stimuli). Variance Ranklets are designed in close analogy with the standard Ranklets, but use the Siegel-Tukey statistics for dispersion instead of the Wilcoxon statistics. Their response shows the same orientation selectivity pattern of Haar wavelets on second-order signals that are not detectable by linear filters. To the best of our knowledge, this is the first family of rank filters designed to detect orientation in variance modulations.We validate our descriptors with an application to texture classification over a subset of the VisTex and Brodatz databases. The combination of standard (intensity) Ranklets with Variance Ranklets greatly improves on the performance of Ranklets alone. Comparison with other published results shows that state-of-the-art recognition rates can be achieved with a simple Nearest Neighbour classifier.

show abstract

Rank-Sum Tests for Dispersions

Cited by 308 publications

References 8 publications

Characterization of the rainy season in Burkina Faso and it’s representation by regional climate models

Characterization of the rainy season in Burkina Faso and it’s representation by regional climate models

Performance of Two Sample Scale Tests: An Empirical Study

Variance Ranklets: orientation–selective rank features for contrast modulations

Contact Info

Product

Resources

About