Time series analysis by the Maximum Entropy method
The principal subject of this report is the use of the Maximum Entropy method for spectral analysis of time series. The classical Fourier method is also discussed, mainly as a standard for comparison with the Maximum Entropy method. Examples are given which clearly demonstrate the superiority of the latter method over the former when the time series is short. The report also includes a chapter outlining the theory of the method, a discussion of the effects of noise in the data, a chapter on significance tests, a discussion of the problem of choosing the prediction filter length, and, most importantly, a description of a package of FORTRAN subroutines for making the various calculations. Cross-referenced program listings are given in the appendices. The report also includes a chapter demonstrating the use of the programs by means of an example. Real time series like the lynx data and sunspot numbers are also analyzed. 22 figures, 21 tables, 53 references.
- Research Organization:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- DOE Contract Number:
- W-7405-ENG-26
- OSTI ID:
- 6461764
- Report Number(s):
- ORNL-5332; TRN: 79-003889
- Country of Publication:
- United States
- Language:
- English
Similar Records
The EGS4 Code System
Comparison of the maximum entropy and exponential series methods for the recovery of distributions of lifetimes from fluorescence lifetime data
Related Subjects
71 CLASSICAL AND QUANTUM MECHANICS
GENERAL PHYSICS
59 BASIC BIOLOGICAL SCIENCES
COMPUTER CODES
DATA ANALYSIS
DIGITAL FREQUENCY ANALYSIS
COMPARATIVE EVALUATIONS
ENTROPY
FOURIER TRANSFORMATION
POPULATION DYNAMICS
STRIPED BASS
SUNSPOTS
TIME DEPENDENCE
ANIMALS
AQUATIC ORGANISMS
FISHES
INTEGRAL TRANSFORMATIONS
PHYSICAL PROPERTIES
SOLAR ACTIVITY
THERMODYNAMIC PROPERTIES
TRANSFORMATIONS
VERTEBRATES
990200* - Mathematics & Computers
640104 - Astrophysics & Cosmology- Solar Phenomena
550100 - Behavioral Biology