My da|ra Login

Detailed view

metadata language: English

Regime-Dependent Recession Forecasts and the 2001 Recession

Resource Type
Dataset : survey data
  • Dueker, Michael J. (Federal Reserve Bank of St. Louis)
Other Title
  • Version 1 (Subtitle)
Publication Date
Free Keywords
economic conditions; economic change; economic indicators; prediction; recession
  • Abstract

    Business recessions are notoriously hard to predict accurately, hence the quip that economists have predicted eight of the last five recessions. This article derives a six-month-ahead recession signal that reduces the number of false signals outside of recession, without impairing the ability to signal the recessions that occur. In terms of predicting the 1990-1991 and 2001 recessions out of sample, the new recession signal, like other signals, largely misses the 1990-1991 recession with its six-month-ahead forecasts. In contrast, a recession onset in April or May 2001 was predicted six months ahead of the 2001 recession, which is close to the actual turning point of March 2001.
  • Table of Contents


    • DS1: Dataset
Geographic Coverage
  • United States
Collection Mode
  • (1) The files submitted are the program file, 0211mdp.txt, and the data file, 0211mdd.txt. (2) These data are part of ICPSR's Publication-Related Archive and are distributed exactly as they arrived from the data depositor. ICPSR has not checked or processed this material. Users should consult the investigator(s) if further information is desired.

This study is freely available to the general public via web download.
Alternative Identifiers
  • 1272 (Type: ICPSR Study Number)
  • Dueker, Michael J.. Regime-dependent recession forecasts and the 2001 recession. Federal Reserve Bank of St. Louis Review.84, (6), 29-36.2002.

Update Metadata: 2015-08-05 | Issue Number: 6 | Registration Date: 2015-06-15

Dueker, Michael J. (2003): Regime-Dependent Recession Forecasts and the 2001 Recession. Version 1. Version: v1. ICPSR - Interuniversity Consortium for Political and Social Research. Dataset.