Forecasting Greek Real GDP Based on ARIMA Modeling

Abstract

The term “economic growth” refers to the increase of real gross national product or gross domestic product or per capita income. National income or else national product is usually expressed as a measure of total added value of a domestic economy known as gross domestic product (GDP). Generally, GDP measures the value of economic activity within a country during a specific time period. The current study aims to find the most suitable model that adjusts on a time-series data set using Box-Jenkins methodology and to examine the forecasting ability of this model. The analysis used quarterly data for Greece from the first quarter of 1995 until the third quarter of 2019. Nonlinear maximum likelihood estimation (maximum likelihood-ML) was applied to estimate the model using the Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm while covariance matrix was estimated using the negative of the matrix of log-likelihood second derivatives (Hessian-observed). Forecasting of the time series was achieved both with dynamic as well as static procedures using all forecasting criteria.

Citation

Dritsaki, C. and Dritsaki, M. (2021), "Forecasting Greek Real GDP Based on ARIMA Modeling", Vlachos, V., Bitzenis, A. and Sergi, B.S. (Ed.) Modeling Economic Growth in Contemporary Greece (Entrepreneurship and Global Economic Growth), Emerald Publishing Limited, Leeds, pp. 45-60. https://doi.org/10.1108/978-1-80071-122-820211005