Time series analysis by the Maximum Entropy method

Technical Report · Mon Jan 01 04:00:00 EST 1979

DOI:https://doi.org/10.2172/6461764· OSTI ID:6461764

Kirk, B L; Rust, B W; Van Winkle, W

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., TN (USA)
• DOE Contract Number: W-7405-ENG-26
• OSTI ID: 6461764
• Report Number(s): ORNL-5332
• Country of Publication: United States
• Language: English

Related Subjects

550100 -- Behavioral Biology
59 BASIC BIOLOGICAL SCIENCES
640104 -- Astrophysics & Cosmology-- Solar Phenomena
71 CLASSICAL AND QUANTUM MECHANICS
GENERAL PHYSICS
99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
ANIMALS
AQUATIC ORGANISMS
COMPARATIVE EVALUATIONS
COMPUTER CODES
DATA ANALYSIS
DIGITAL FREQUENCY ANALYSIS
ENTROPY
FISHES
FOURIER TRANSFORMATION
INTEGRAL TRANSFORMATIONS
PHYSICAL PROPERTIES
POPULATION DYNAMICS
SOLAR ACTIVITY
STRIPED BASS
SUNSPOTS
THERMODYNAMIC PROPERTIES
TIME DEPENDENCE
TRANSFORMATIONS
VERTEBRATES