Speculative bubbles in present-value models: A Bayesian Markov-switching state space approach

We estimate the dynamics of a speculative bubble subject to surviving and collapsing regime together with dividends returns in tractable state space specification present-value model. To this new high-dimensional model, we develop an efficient Markov chain Monte Carlo sampler simulate from joint posterior distribution. find that real-world stock price bubbles show significant Markov-switching structure. Further, results indicate dividend growth rates are highly predictable. Finally, variation explains large share price-dividend ratio unexpected return.