Incorporating vintage differences and forecasts into Markov switching models

This paper incorporates vintage differences and forecasts into the Markov switching models described by . The vintage differences and forecasts induce parameter breaks close to the end of the sample, too close for standard maximum likelihood techniques to produce precise parameter estimates. A supplementary procedure estimates the statistical properties of the end‐of‐sample observations that behave differently from the rest, allowing inferred probabilities to reflect the breaks. Empirical results using real‐time data show that these techniques improve the ability of a Markov switching model based on GDP and GDI to recognize the start of the 2001 recession.