Digital Library of the European Council for Modelling and Simulation

Title:	Econometric Modelling Of Time Series Relationship Between Fertility And Income For The Russian Population: Methodological Issues
Authors:	Oksana Shubat, Anna Bagirova
Published in:	(2018). ECMS 2018 Proceedings Edited by: Lars Nolle, Alexandra Burger, Christoph Tholen, Jens Werner, Jens Wellhausen European Council for Modeling and Simulation. doi: 10.7148/2018-0005 ISSN: 2522-2422 (ONLINE) ISSN: 2522-2414 (PRINT) ISSN: 2522-2430 (CD-ROM) 32nd European Conference on Modelling and Simulation, Wilhelmshaven, Germany, May 22^nd – May 26^5h, 2018
Citation format:	Oksana Shubat, Anna Bagirova (2018). Econometric Modelling Of Time Series Relationship Between Fertility And Income For The Russian Population: Methodological Issues, ECMS 2018 Proceedings Edited by: Lars Nolle, Alexandra Burger, Christoph Tholen, Jens Werner, Jens Wellhausen European Council for Modeling and Simulation. doi: 10.7148/2018-0020
DOI:	https://doi.org/10.7148/2018-0020
Abstract:	Finding determinants of demographic processes is a highly topical issue in countries with negative demographic trends. Our research was aimed at studying the relationships between fertility and income indicators in Russia. The period under review was 2000 to 2016. To explore the correlation between the time series, we used the methodology of estimating trend deviation. We applied analytical smoothing to model trends, estimating regression models. To assess the strength of relationship between the time series, we analysed correlation between regressions’ residuals. The results of our analysis showed no relationship between people’s incomes and fertility rates. The research we carried out into time series dynamics did not confirm the results of other studies based on static data. Accordingly, this raises questions about the methodology for analyzing the relationship between dynamic processes with a high volatility of input data. Evidently to receive reliable and stable results, multi-dimensional analysis methods should be integrated into the study of relationships between dynamic time series, including preliminary multi-dimensional data classification. This will enable carrying out analysis on homogenous territorial or temporal segments, which would be more methodologically sound.
Full text: