Open AccessA Comparative Study of Fourier Series Models and Seasonal -Autoregressive Integrated Moving Average Model of Rainfall Data in Port Harcourt
Author(s) -
Wiri Leneenadogo,
Sibeate Pius U
Publication year - 2021
Publication title -
asian journal of probability and statistics
Language(s) - English
Resource type - Journals
ISSN - 2582-0230
DOI - 10.9734/ajpas/2020/v10i330249
Subject(s) - autoregressive integrated moving average , akaike information criterion , port harcourt , autoregressive model , seasonality , mathematics , series (stratigraphy) , time series , moving average , statistics , moving average model , fourier series , autoregressive–moving average model , econometrics , geology , mathematical analysis , paleontology , socioeconomics , sociology
This study compares the Seasonal autoregressive integrated moving average (SARIMA) model within Fourier time series model in modelling rainfall data in Port Harcourt Rivers State from 2000-2014. The time plot of the series showed Seasonality but a not obvious trend. The raw data is nonstationary at the level. Time plot of the seasonal differencing of rainfall at lag12 showed a stationary process with seasonality at lag 12 on the PACF and ACF of the series. The periodogram plot reveals that there exist both short and long term cycles within the period. The Fourier series and the seasonal autoregressive moving average models are reduced to 12month of seasonal component.( ) The Akaike Information Criterion (AIC) was used to select better models. The best model is the model that minimises the information criterion. It was observed that SARIMA (1,0,1)(1,1,1)12 models have a minimum AIC value. Hence, SARIMA model performs better in modelling the rainfall data in Port Harcourt then the Fourier series models.