Time series analysis and signal processing
Sikandar Kumar, Prabin Kumar Bora · 2012
Summary form only given. Time series analysis is the analysis of the data collected sequentially in time. These data are usually represented as linear/nonlinear discrete-time models. The time-series models are used to analyse and predict the data. A linear time series is modeled by linear difference equations involving the time series and the white noise or the innovation process. Such ARMA(p, q) models can be analysed using the linear system theory. Signal processing tools can be used to estimate the parameters of the model. Alternatively, the time series data can be analysed in the frequency domain in terms of the power spectral density. This paper gives a brief theoretical background on the ARMA (p, q) models and the power spectral analysis of time-series data.