0452315 20240903115740.120151216235959.9 000349860900005 84922361174 10.1103/PhysRevE.91.022802 5 s. P cav_un_epca*00217521539-3755911 (2015)American Physical Society Detrended cross-correlation analysis Regression Scales cav_un_auth*0256902 Krištoufek Ladislav Ekonometrie Department of Econometrics E E UTIA-B Department of Econometrics 100 Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2015/E/kristoufek-0452315.pdf GAP402/11/0948 GA ČR CZ cav_un_auth*0284442 GP14-11402P GA ČR CZ cav_un_auth*0303546 We propose a framework combining detrended fluctuation analysis with standard regression methodology. The method is built on detrended variances and covariances and it is designed to estimate regression parameters at different scales and under potential nonstationarity and power-law correlations. The former feature allows for distinguishing between effects for a pair of variables from different temporal perspectives. The latter ones make the method a significant improvement over the standard least squares estimation. Theoretical claims are supported by Monte Carlo simulations. The method is then applied on selected examples from physics, finance, environmental science, and epidemiology. For most of the studied cases, the relationship between variables of interest varies strongly across scales. 2016 AH 1 RVO:67985556 http://hdl.handle.net/11104/0253720 1 S PHYSICS.FLUIDS&PLASMAS|PHYSICS.MATHEMATICAL 2.233 0.547 9 0.15232 0.828 83841 1.183 Q1 1.738 2466 Q1 79 Q2 Q1 89.623 2015 84922361174 SCOPUS 000349860900005 WOS cav_un_epca*0021752 Physical Review E 1539-3755 2470-0053 Roč. 91 č. 1 2015 , 022802-1-022802-5 American Physical Society