PABLO MARSHALL () (Escuela de Administración, Pontificia Universidad Católica de Chile)
Abstract
This study considers different methodologies for times series prediction of Sales. Given the specification of a bivariate autoregressive time series model for Sales and GDP, the paper derives classical models of prediction, such as a regression model, a regression model with error correction, a transfer function, and an ARIMA model. The study discusses the relevance of these models when the Sales series are cointegrated with GDP and when they are not. Results for 20 quarterly Sales time series between 1983 y 1996, show that GDP does not significantly explain short-term variations in Sales. The long-term variations in sales are completely explained by GDP in 6 out of the 20 series. The best results for short-term out-of-sample predictions are obtained with the ARIMA model. For long-term predictions, if the Sales time series are cointegrated with the GDP, the best is the regression model. Otherwise, the ARIMA model gives better results. The results of this study are a contribution to the selection of the best methodologies for short- and long-term time series prediction of Sales.
Download Info
To download:
If you experience problems downloading a file, check if you have the
proper application to
view it first. Information about this may be contained
in the File-Format links below. In case of further problems read
the IDEAS help
page. Note that these files are not on the IDEAS
site. Please be patient as the files may be large.
Publisher Info
Article provided by Escuela de Administracion. Pontificia Universidad Católica de Chile. in its journal ABANTE.
Find related papers by JEL classification: C13 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods: General - - - Estimation M10 - Business Administration and Business Economics; Marketing; Accounting - - Business Administration - - - General
References listed on IDEAS Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.: