Please use this identifier to cite or link to this item:
|Title:||Does the Box-Cox transformation help in forecasting macroeconomic time series?|
Discipline of Business Analytics
Nonparametric estimation of prediction error variance
|Abstract:||The paper investigates whether transforming a time series leads to an improvement in forecasting accuracy. The class of transformations that is considered is the Box-Cox power transformation, which applies to series measured on a ratio scale. We propose a nonparametric approach for estimating the optimal transformation parameter based on the frequency domain estimation of the prediction error variance, and also conduct an extensive recursive forecast experiment on a large set of seasonal monthly macroeconomic time series related to industrial production and retail turnover. In about one fifth of the series considered the Box-Cox transformation produces forecasts significantly better than the untransformed data at one-step-ahead horizon; in most of the cases the logarithmic transformation is the relevant one. As the forecast horizon increases, the evidence in favour of a transformation becomes less strong. Typically, the naïve predictor that just reverses the transformation leads to a lower mean square error than the optimal predictor at short forecast leads. We also discuss whether the preliminary in-sample frequency domain assessment conducted provides a reliable guidance which series should be transformed for improving significantly the predictive performance.|
|Department/Unit/Centre:||Discipline of Business Analytics|
|Type of Work:||Working Paper|
|Appears in Collections:||Working Papers - Business Analytics|
This work is protected by Copyright. All rights reserved. Access to this work is provided for the purposes of personal research and study. Except where permitted under the Copyright Act 1968, this work must not be copied or communicated to others without the express permission of the copyright owner. Use the persistent URI in this record to enable others to access this work.
|OMWP_2011_08.pdf||219.2 kB||Adobe PDF||View/Open|
Items in Sydney eScholarship Repository are protected by copyright, with all rights reserved, unless otherwise indicated.