Prediction of steel prices: A comparison between a conventional regression model and MSSA

Autor:	Werner G. Müller, Martin Kapl
Rok vydání:	2010
Předmět:	Statistics and Probability Series (mathematics) Applied Mathematics Econometrics Regression analysis Autoregressive integrated moving average Singular spectrum analysis Class (biology) Simulation Mathematics
Zdroj:	Statistics and Its Interface. 3:369-375
ISSN:	1938-7997 1938-7989
DOI:	10.4310/sii.2010.v3.n3.a10
Popis:	In this paper we compare two forecast procedures by its capabilities to predict market steel prices. One is based on the classical Box-Jenkins ARIMA class, the other on multichannel singular spectrum analysis (MSSA). We find the two approaches competitive with an advantage for MSSA to be expected as the time series grow longer.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::df697ea8a2cd8ae12e8cc8572bf07a74 https://doi.org/10.4310/sii.2010.v3.n3.a10 Zobrazit plný text záznamu