Predicting Ordinary and Severe Recessions with a Three-State Markov-Switching Dynamic Factor Model. An Application to the German Business Cycle

Abstract

We estimate a Markow-switching dynamic factor model with three states based on six leading business cycle indicators for Germany preselected from a broader set using the Elastic Net softthresholding rule. The three states represent expansions, normal recessions and severe recessions. We show that a two-state model is not sensitive enough to reliably detect relatively mild recessions when the Great Recession of 2008/2009 is included in the sample. Adding a third state helps to clearly distinguish normal and severe recessions, so that the model identifies reliably all business cycle turning points in our sample. In a real-time exercise the model detects recessions timely. Combining the estimated factor and the recession probabilities with a simple GDP forecasting model yields an accurate nowcast for the steepest decline in GDP in 2009Q1 and a correct prediction of the timing of the Great Recession and its recovery one quarter in advance.JEL-Codes: C530, E320, E370.

Markov-switching state-space models with applications to neuroimaging

“…Switching state-space models Switching SSMs have an extensive track record of applications in fields as diverse as control engineering (Chang and Athans, 1978;Melnyk et al, 2016), econometrics (Hamilton, 1990;Kim, 1994;Camacho et al, 2018;Carstensen et al, 2020), speech recognition (Deng, 2004;Rosti and Gales, 2004), computer vision (Bregler, 1997) and neuroimaging (Prado, 2013;Samdin et al, 2017;Taghia et al, 2017;Ombao et al, 2018). These models, also called 1 arXiv:2106.05092v1 [stat.ME] 9 Jun 2021 switching dynamic factor models, include switching regression (Goldfeld and Quandt, 1973;Cosslett and Lee, 1985) and switching vector autoregressive models (Krolzig, 1997;Yang, 2000;Lanne et al, 2010;Ting et al, 2018) as special cases.…”

Markov-Switching State-Space Models with Applications to Neuroimaging

“…Switching state-space models Switching SSMs have an extensive track record of applications in fields as diverse as control engineering (Chang and Athans, 1978;Melnyk et al, 2016), econometrics (Hamilton, 1990;Kim, 1994;Camacho et al, 2018;Carstensen et al, 2020), speech recognition (Deng, 2004;Rosti and Gales, 2004), computer vision (Bregler, 1997) and neuroimaging (Prado, 2013;Samdin et al, 2017;Taghia et al, 2017;Ombao et al, 2018). These models, also called switching dynamic factor models, include switching regression (Goldfeld and Quandt, 1973;Cosslett and Lee, 1985) and switching vector autoregressive models (Krolzig, 1997;Yang, 2000;Lanne et al, 2010;Ting et al, 2018) as special cases.…”