An Analysis on the Unemployment Rate in the Philippines: A Time Series Data Approach

5th International Conference on Science & Engineering in Mathematics, Chemistry and Physics 2017

数学;化学;物理学

Urrutia, J.D.^1 ; Tampis, R.L.^2 ; Atienza, J.B.E.^3

Center for Statistical Studies, Institute for Data and Statistical Analysis, Polytechnic University of the Philippines, Sta. Mesa, Manila, Philippines^1

Polytechnic University of the Philippines, Parañaque Campus, Philippines^2

Department of Mathematics and Statistics, College of Science, Polytechnic University of the Philippines, Sta. Mesa, Manila, Philippines^3

关键词: Causal relationships;    Co-integration tests;    Granger causality test;    Gross domestic products;    Gross national incomes;    Independent variables;    National statistics;    Unemployment rates;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/820/1/012008/pdf
DOI  :  10.1088/1742-6596/820/1/012008

来源: IOP

【 摘 要 】

This study aims to formulate a mathematical model for forecasting and estimating unemployment rate in the Philippines. Also, factors which can predict the unemployment is to be determined among the considered variables namely Labor Force Rate, Population, Inflation Rate, Gross Domestic Product, and Gross National Income. Granger-causal relationship and integration among the dependent and independent variables are also examined using Pairwise Granger-causality test and Johansen Cointegration Test. The data used were acquired from the Philippine Statistics Authority, National Statistics Office, and Bangko Sentral ng Pilipinas. Following the Box-Jenkins method, the formulated model for forecasting the unemployment rate is SARIMA (6, 1, 5) × (0, 1, 1)4with a coefficient of determination of 0.79. The actual values are 99 percent identical to the predicted values obtained through the model, and are 72 percent closely relative to the forecasted ones. According to the results of the regression analysis, Labor Force Rate and Population are the significant factors of unemployment rate. Among the independent variables, Population, GDP, and GNI showed to have a granger-causal relationship with unemployment. It is also found that there are at least four cointegrating relations between the dependent and independent variables.