Please use this identifier to cite or link to this item:
|Title||Generation of PAR Time Series Models Using Periodic Levinson-Durbin Algorithm|
Time Series analysis can be used to extract information hidden in data. The classical techniques for Time Series data analysis are the linear Time Series models including the Moving Average Models (MA), the Autoregressive Models (AR) and the Autoregressive Moving Average Models (ARMA). We will mention and display these three models in details, and will show the important characteristics and methods of finding their parameters, autocovariance and autocorrelation functions. We will present a detailed explanation of the Ordinary and Periodically Correlated Time Series in a simple and easy way for everyone interested in this field. The main goal of this thesis is to generate the varying orders of PAR models by using Periodic Levinson-Durbin algorithm and the Periodic Partial Autocorrelation function (PePACF) which play a main role in determination the orders of the PAR models. To avoid the difficulties that may confront us in the manual calculations of PAR model’s parameters and make the way more effective, we presented a developed practical code on the R .
|Publisher||الجامعة الإسلامية - غزة|
|Files in this item|