How Can We Extract a Fundamental Trend from an Economic Time- Series?
This paper attempts to extract a fundamental trend, which we call a " trend-cycle component," from an economic time-series. The "trend-cycle component" consists of a medium-term business cycle component and a long- term trend component. The objective is to eliminate the short-term irregular and seasonal variations that hide a fundamental trend in an economic time-series. We test five different time-series methods. Among them, the Henderson moving average (which is incorporated in an X-12- ARIMA seasonal adjustment program), the Band-Pass filter (which utilizes a Fourier transformation), and the DECOMP are found to be effective in extracting a "trend-cycle component" with a cyclical period longer than 1 .5 years. However, no method is found to be effective in extracting a " long-term trend component" with a cyclical period longer than that of a medium-term business cycle. Although the HP filter is somewhat successful , it still contains a component with a cyclical period of about three years that corresponds to a business cycle. These methods are useful for forecasting a wide variety of economic variables because they reveal a fundamental trend in the time series. In addition, statistical programs are available for easy application. They have, however, a few shortcomings. First, it is often difficult to provide a meaningful economic interpretation of the revealed characteristics of the "trend- cycle component." Second, the addition of new data can change the estimation results. In particular, an extracted component around the end of a sample period is likely to be revised with new data. Special caution is in order, therefore, in interpreting the estimation results and forecasting the time series when the data exhibit large variations. In this case, comparing the results of different methods provides a useful way to assess the reliability of an extracted "trend-cycle component."
Volume (Year): 16 (1998)
Issue (Month): 2 (December)
|Contact details of provider:|| Postal: 2-1-1 Nihonbashi, Hongoku-cho, Chuo-ku, Tokyo 103|
Web page: http://www.imes.boj.or.jp/
More information through EDIRC
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.:
- Kiyotaki, Nobuhiro & Moore, John, 1997.
Journal of Political Economy,
University of Chicago Press, vol. 105(2), pages 211-248, April.
- Ryo Kato, 2003. "Matlab code for Kiyotaki-Moore credit cycles," QM&RBC Codes 113, Quantitative Macroeconomics & Real Business Cycles.
- Nobuhiro Kiyotaki & John Moore, 1995. "Credit Cycles," NBER Working Papers 5083, National Bureau of Economic Research, Inc.
- John Moore & Nobuhiro Kiyotaki, "undated". "Credit Cycles," Discussion Papers 1995-5, Edinburgh School of Economics, University of Edinburgh.
- Michael F. Bryan & Stephen G. Cecchetti, 1993.
"Measuring Core Inflation,"
NBER Working Papers
4303, National Bureau of Economic Research, Inc.
When requesting a correction, please mention this item's handle: RePEc:ime:imemes:v:16:y:1998:i:2:p:61-111. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Kinken)
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
If references are entirely missing, you can add them using this form.
If the full references list an item that is present in RePEc, but the system did not link to it, you can help with this form.
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your profile, as there may be some citations waiting for confirmation.
Please note that corrections may take a couple of weeks to filter through the various RePEc services.