Simulation of estimating periodicity of seasonally stationary time series
Herein, some common periodicity estimation methods: the periodogram analysis, the maximum entropy spectral method, the successive average method as well as the graphic method are considered. For comparing these methods and verifying their practical efficiency, simulations are performed on several groups of seasonal stationary time series which are generated by the model x(t) = v(t) + z(t). v(t) being a seasonal component with different forms (Sinusoid, unequal amptitude oscillation, slope signal, exponential decay signal and block signal etc.) and z(t) being autoregressive process under different levels of signal-noise ratio. Computational results, comprehensively illustrate that the successive average method is easier to carry out and more efficient in practice.
- Research Organization:
- Brookhaven National Lab., Upton, NY (USA)
- DOE Contract Number:
- AC02-76CH00016
- OSTI ID:
- 6188646
- Report Number(s):
- BNL-35384; CONF-840855-1; ON: DE85003517
- Resource Relation:
- Conference: International conference on energy modelling and simulation, Minneapolis, MN, USA, 13 Aug 1984
- Country of Publication:
- United States
- Language:
- English
Similar Records
An Easy Algorithm to Generate Colored Noise Sequences
Optimal Frequency-domain Analysis for Spacecraft Time Series: Introducing the Missing-data Multitaper Power Spectrum Estimator