Multivariate Adaptive Regression Splines (Mars) Method For Unemployment in OECD Countries

Unemployment is one of the most important macroeconomic problems in all countries and it is very important task for identification of the key determinants of it. Therefore, in recent years determining the factors affecting the unemployment is attracting the researcher. In this study, the factors affecting unemployment in Organization for Economic Co-operation and Development (OECD) countries were tried to be determined. In this context, data for the years 2000-2017 were analyzed by using MARS method. For each year, we estimated the Multivariate Adaptive Regression Splines (MARS) models and we tracked the effective predictors. According to our findings, the indicators Gross domestic product (Gdp), tax revenue rate, long term interest rate, saving rate and inflation usually have a significant impact on the unemployment rates. The annual growth rate of import, export and exchange rate do not influence the unemployment ratios. Besides these results, the industrial production, the industrial value added and current account balance are influential for a few years.

Anahtar Kelimeler:

Multivariate Adaptive Regression Splines (MARS), Unemployment Rate, OECD

Multivariate Adaptive Regression Splines (Mars) Method For Unemployment in OECD Countries

PDF

___

[1] Gatti, D., Vaubourg, A.G. 2010. The Financial Determinants of Unemployment: do they interact with labor market institutions?. Wiliam Davidson Institute Working Paper, Vol.273.
[2] Gyekye, K.B., Kyei, K.A. 2011. Determinants of unemployment in Limpopo province in South Africa: exploratory studies. Journal of Emerging Trends in Economics and Management Sciences, 2(1), 54-61.
[3] Güriş, S., Yaman, B. 2018. OECD Ülkelerinde İşsizliği Etkileyen Faktörlerin Panel Veri Modelleri ile Analizi. Social Sciences Research Journal, C, 7, 136-146.
[4] Bayrak, R., Tatli, H. 2018. The Determinants of Youth Unemployment: A Panel Data Analysis of OECD Countries. The European Journal of Comparative Economics, 15(2), 231-248.
[5] Bruno, G.S., Choudhry Tanveer, M., Marelli, E., Signorelli, M.2017. The short-and long-run impacts of financial crises on youth unemployment in OECD countries. Applied Economics, 49(34), 3372-3394.
[6] Uzunkaya, S. Ş., Dinçer, H., Yüksel, S. 2019. ABD’nin Ekonomik Gelişmesinin Tarihsel Bir Analizi (1947-2017). MANAS Sosyal Araştırmalar Dergisi, 8(1/1), 215-228.
[7] Dinçer, H., Hacıoğlu Ü., Yüksel, S. 2017. Determining Influencing Factors of Currency Exchange Rate for Decision Making in Global Economcy using MARS Method. Chapter 13: Geopolitics and Strategic Management in the Global Economy, IGA Global.
[8] Bolder, J., Rubin, T. 2007. Optimization in a Simulation Setting: Use of Function Approximation in Debt Strategy Analysis. Bank of Canada Working Paper, 1-92.
[9] Yüksel, S., Zengin S., Kartal, M.T. 2016. Identifying the Macroeconomic Factors Influencing Credit Card Usage in Turkey by Using MARS Method. China-USA Business Review, 15(12), 611-615.
[10] Friedman, J.H. 1991. Multivariate adaptive regression splines. The annals of statistics, 19(1), 1-67.
[11] Lee, T.S., Chiu, C.C., Chou, Y.C., Lu, C.J.2006. Mining the customer credit using classification and regression tree and multivariate adaptive regression splines. Computational Statistics & Data Analysis, 50(4), 1113-1130.
[12] Friedman, J., Hastie, T., Tibshirani, R. 2001. The elements of statistical learning. Vol. 1, No. 10, New York: Springer series in statistics.
[13] Salford Systems, 2001. TreeNet stochastic gradient boosting: An implementation of the MART methodology.
[14] Craven, P., Wahba, G. 1979. Estimating the correct degree of smoothing by the method of generalized cross-validation”, Numerische Mathematik, 31, 377-403.