TY - JOUR
T1 - Using statistical process monitoring to identify us business cycle change points and turning points
AU - Enck, David
AU - Beruvides, Mario
AU - Tercero-Gómez, Víctor G.
AU - Cordero-Franco, Alvaro E.
N1 - Publisher Copyright:
© 2021 Informa UK Limited, trading as Taylor & Francis Group.
PY - 2021
Y1 - 2021
N2 - The Business Cycle paradigm of Mitchell and Burns has evolved from their original goal of understanding the entire economic process to the binary identification of growth and recessionary Turning Points. We propose a new paradigm for modelling the Business Cycle based on the Statistical Process Monitoring technique of Self-Starting Cumulative Sum (SSCUSUM) control charts. The SSCUSUM charts provide continuous characterization of aggregate economic activity through the identification of changes in the mean or standard deviation of economic indicators. A case study is conducted using real GDP % growth between 1965 and 2020 which shows that SSCUSUM charts: identify periods of steady state performance with statistically differentiable means and/or standard deviations, reliably reproduce the National Bureau of Economic Research Business Cycle Turning Points, identify patterns of economic activity leading up to and away from recessions, and identify twice the information on economic performance as the current bivariate approach. Over the study period, the SSCUSUM method identifies 42 changes in the mean or standard deviation of real GDP % growth, while the NBER TPs identify 8 peaks and 7 troughs.
AB - The Business Cycle paradigm of Mitchell and Burns has evolved from their original goal of understanding the entire economic process to the binary identification of growth and recessionary Turning Points. We propose a new paradigm for modelling the Business Cycle based on the Statistical Process Monitoring technique of Self-Starting Cumulative Sum (SSCUSUM) control charts. The SSCUSUM charts provide continuous characterization of aggregate economic activity through the identification of changes in the mean or standard deviation of economic indicators. A case study is conducted using real GDP % growth between 1965 and 2020 which shows that SSCUSUM charts: identify periods of steady state performance with statistically differentiable means and/or standard deviations, reliably reproduce the National Bureau of Economic Research Business Cycle Turning Points, identify patterns of economic activity leading up to and away from recessions, and identify twice the information on economic performance as the current bivariate approach. Over the study period, the SSCUSUM method identifies 42 changes in the mean or standard deviation of real GDP % growth, while the NBER TPs identify 8 peaks and 7 troughs.
KW - Markov model
KW - NBER business cycle dating committee
KW - Self starting cumulative sum control chart
KW - gross domestic product % growth
UR - http://www.scopus.com/inward/record.url?scp=85113812545&partnerID=8YFLogxK
U2 - 10.1080/00036846.2021.1908514
DO - 10.1080/00036846.2021.1908514
M3 - Article
AN - SCOPUS:85113812545
SN - 0003-6846
VL - 53
SP - 5319
EP - 5336
JO - Applied Economics
JF - Applied Economics
IS - 46
ER -