Forecasting Spanish Unemployment Using Near Neighbour and Neural Net Techniques

Autor:	Elena Olmedo
Rok vydání:	2013
Předmět:	Nonlinear system Generality Artificial neural network Robustness (computer science) media_common.quotation_subject Economics Econometrics and Finance (miscellaneous) Unemployment Economics Econometrics Time horizon Probabilistic forecasting Computer Science Applications media_common
Zdroj:	Computational Economics. 43:183-197
ISSN:	1572-9974 0927-7099
DOI:	10.1007/s10614-013-9371-1
Popis:	In this paper, alternative non-parametric forecasting techniques are analysed, with emphasis placed on the difference between the reconstruction and learning approaches. The former is based on Takens' Theorem, which recovers unknown dynamic properties of a system; it is appropriate in deterministic systems. The latter is a powerful instrument in noisy systems. Both techniques are applied to the forecasting of Spanish unemployment, first one step -forecasting and second using a longer time horizon of prediction. To assess the robustness and generality of the methods we have employed unemployment time series of different European countries.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::dd6599d0f6ca1bc582a8f8110a0127aa https://doi.org/10.1007/s10614-013-9371-1 Zobrazit plný text záznamu Full text from SpringerLink