A multidimensional version of the Kolmogorov-Smirnov test Export

@article{citeulike:707413, abstract = {A generalization of the classical Kolmogorov-Smirnov test, suitable for the analysis of large random samples defined in two or three dimensions, is proposed which is faster by a factor equal to the sample size. The present method takes into account the dependence of the test statistics on the degree of correlation of data points and on the sample size. The test is supported by a large number of Monte Carlo simulations, and it is suggested to be distribution-free. An analytical expression for determining the critical values of the test probability distribution is given. The test is demonstrated with an analysis of models of the cosmological evolution of X-ray selected active galactic nuclei, and it is found to be more sensitive than the chi-squared technique.}, author = {Fasano, G. and Franceschini, A.}, citeulike-article-id = {707413}, citeulike-linkout-0 = {http://adsabs.harvard.edu/abs/1987MNRAS.225..155F}, day = {1}, journal = {Monthly Notices of the Royal Astronomical Society}, keywords = {2d, 3d, correlation, independence, kstest, statistics}, month = {March}, pages = {155--170}, posted-at = {2006-06-22 16:08:44}, priority = {2}, title = {A multidimensional version of the Kolmogorov-Smirnov test}, url = {http://adsabs.harvard.edu/abs/1987MNRAS.225..155F}, volume = {225}, year = {1987} }

TY - JOUR ID - citeulike:707413 L3 - citeulike-article-id:707413 N2 - A generalization of the classical Kolmogorov-Smirnov test, suitable for the analysis of large random samples defined in two or three dimensions, is proposed which is faster by a factor equal to the sample size. The present method takes into account the dependence of the test statistics on the degree of correlation of data points and on the sample size. The test is supported by a large number of Monte Carlo simulations, and it is suggested to be distribution-free. An analytical expression for determining the critical values of the test probability distribution is given. The test is demonstrated with an analysis of models of the cosmological evolution of X-ray selected active galactic nuclei, and it is found to be more sensitive than the chi-squared technique. JF - Monthly Notices of the Royal Astronomical Society EP - 170 TI - A multidimensional version of the Kolmogorov-Smirnov test VL - 225 SP - 155 KW - 2d KW - 3d KW - correlation KW - independence KW - kstest KW - statistics AU - Fasano, G AU - Franceschini, A PY - 1987/03/01/ UR - http://adsabs.harvard.edu/abs/1987MNRAS.225..155F ER -