A study on the effect of power transformation in the ARMA(p,q) model
In time series analysis, the Box-Cox power transformation is generally used for variance stabilization. In this paper we show that the order and the first step ahead forecast of the transformed model are approximately invariant to those of the original model under certain assumptions on the mean and variance. A small Monte Carlo simulation is performed to support the results.
Year of publication: |
2001
|
---|---|
Authors: | Shin, Key-Il ; Kang, Hee-Jeong |
Published in: |
Journal of Applied Statistics. - Taylor & Francis Journals, ISSN 0266-4763. - Vol. 28.2001, 8, p. 1019-1028
|
Publisher: |
Taylor & Francis Journals |
Saved in:
Saved in favorites
Similar items by person
-
A Multivariate Unit Root Test Based on the Modified Weighted Symmetric Estimator for VAR(p)
Shin, Key-Il, (2004)
-
A Shrinked Forecast in Stationary Processes Favouring Percentage Error
Park, Heungsun, (2006)
-
A Shrinked Forecast in Stationary Processes Favouring Percentage Error
Park, Heungsun, (2006)
- More ...