Combining Econometric and Time Series Models to Project Albanian Population (Projection for Years 2015- 2023)
Eralda Dhamo (Gjika)1, Oriana Zaçaj2, Edionada Gjika3
1Eralda Dhamo (Gjika), Department of Applied Mathematics, Faculty of Natural Science, University of Tirana, Tirana, Albania.
2Oriana Zaçaj, Department of Mathematics, Faculty of Mathematics and Physic Engineering, Polytechnic University Tirana, Albania.
3Edionada Gjika, Department of Biotechnology, Faculty of Natural Science, University of Tirana, Tirana, Albania.
Manuscript received on November 12, 2015. | Revised Manuscript received on November 21, 2015. | Manuscript published on November 25, 2015. | PP: 1-4 | Volume-4 Issue-1, November 2015. | Retrieval Number: A1044114115
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Albania is a small country in the Balkan region but with a key geographical position in the demographic movements in the region and in Europe. In the recent years the political and economic changes in Europe have significantly affected demographic indicators of the country. The population projection is one of the important issues in this moment. The number of births is decreasing, by other hand number of emigrants is increasing rapidly. At this moment population forecasting techniques are seen with interest. In this work we study many socioeconomic variables that may affect the total number of population in Albania. We propose two models which may be used to projected population in the upcoming years. The models combine multiple regression and time series models. The most important variables in the model were selected based on many indicators of the model (AIC, MAPE, MSE etc.) and graphical tests. The final model was selected based on several measures of accuracy and bias, and formal statistical tests of differences in errors by technique.
Keywords: Population projection, time series, regression, socioeconomics, accuracy