Abstract.

The smoothing of time series describing the dynamics of some indicators is considered. The need in smoothing is caused by a considerable random dispersion of indicators magnitude. The smoothing method based on grouping of similar time series samples is proposed. For measure of similarity the correlation factor is used.

Keywords:

dynamic objects, statistic estimation, indicators.

pp. 58-62

References

1. Bauman E.V., Dorofeyuk, A.A. Cluster-analysis. / Proceedings of the International conference on control science, Vol. 1. -M.: SINTEG, 1999, pp. 62-67. (in Russian).
2. Bauman E.V., Dorofeyuk, A.A., Dorofeyuk J.A. Dynamic structural analysis of multidimensional objects. / Proceedings of the IV International conference on control science (MKPU-IV). -M.: ICS RAS, 2009, pp. 338-343. (in Russian).
3. Aivazyan S.A., Enyukov I.S., Meshalkin L.D. Applied statistics: dependence analysis. -M.: Finances and statistics, 1985.