Statistical error in a chord estimator of correlation dimension: the ``rule of five''
James Theiler, Turab Lookman
Abstract
The statistical precision of a chord method for estimating fractal dimension from a correlation integral is derived. The optimal chord length is determined, and a comparison is made to other estimators. These calculations use the approximation that all pairwise distances between the points are statistically independent; the adequacy of this approximation is assessed numerically. The chord method provides a very quick and easy dimension estimate which is only slightly less precise than the optimal estimator. Keywords: correlation dimension, statistical error
Create a lesson
Related papers
A new discrete velocity method for Navier-Stokes equations
Michael Junk, S. V. Raghurama Rao
Construction of Molecular Dynamics Like Cellular Automata Models for Simulation of Compressible Fluid Dynamic Systems
Himanshu Agrawal
Lattice Gases and Cellular Automata
Bruce M. Boghosian
Cellular Automaton Rule184++C. A Simple Model for the Complex Dynamics of Various Particles Flow
A. Awazu
Exact results for deterministic cellular automata traffic models
Henryk Fuks
Crystalline Computation
Norman Margolus