Many current seasonally adjusted level data are based on Census-X-11-type moving average filters applied to past and forecasted log-transformed observations, which is usually called the Census-X-11 ARIMA method. The forecasts are often generated from seasonal ARIMA models for the log-transformed time series. The seasonally adjusted level data are obtained by taking exponential of the adjusted logged data. In this paper we show that this leads to a systematic downward bias in the adjusted levels data. For an exemplary seasonal ARIMA model we provide an explicit expression of this bias in two specific cases. Our general recommendation is that one should consider such expressions for any specific series.
Download Info
To our knowledge, this item is not available for
download. To find whether it is available, there are three
options:
1. Check below under "Related research" whether another version of this item is available online.
2. Check on the provider's web page
whether it is in fact available.
3. Perform a search for a similarly titled item that would be
available.
Publisher Info
Paper provided by Erasmus University of Rotterdam - Econometric Institute in its series Papers with number
9717/a.
Find related papers by JEL classification: C12 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods: General - - - Hypothesis Testing C22 - Mathematical and Quantitative Methods - - Single Equation Models; Single Variables - - - Time-Series Models; Dynamic Quantile Regressions
Cited by: (explanations, 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.)