Open AccessStudying the Stability of Some Non-Linear Time Series Models with Application
Author(s) -
Abdulghafoor J. Salim,
Nihad Shareef Khalaf
Publication year - 2008
Publication title -
maǧallaẗ al-rāfidayn li-ʿulūm al-ḥāsibāt wa-al-riyāḍiyyāẗ/al-rafidain journal for computer sciences and mathematics
Language(s) - English
Resource type - Journals
eISSN - 2311-7990
pISSN - 1815-4816
DOI - 10.33899/csmj.2008.163988
Subject(s) - series (stratigraphy) , mathematics , stability (learning theory) , autoregressive integrated moving average , linear model , logarithm , polynomial and rational function modeling , transformation (genetics) , time series , polynomial , computer science , statistics , mathematical analysis , biology , gene , paleontology , machine learning , biochemistry , chemistry
In this paper we study the stability of time series models in general, and for some non-linear time series models as a special case. Lagrange method to find the stability of non-linear models has been given. The Leishmaniasis time series was studied and modeled by different non-linear models such as, seasonal ARIMA model by using the logarithmic transformation, exponential model of order two and the polynomial model. The stability of all such models by the above method has been obtained. From the comparison we find that the SARIMA is the best among all such models which we used for forecasting one year ago.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom