Bayesian estimation of parameters of a damped sinusoidal model by a Markov chain Monte Carlo method

A dynamic Monte Carlo method is proposed to compute the posterior means and covariances of the parameters of a damped sinusoidal model when an informative prior distribution is known. The Bayesian framework provides a sound mathematical ground, which possibly allows one to overcome the approximations commonly used to cope with this difficult problem. Some simulations results are provided, which support the conclusion that the prior information can also be significantly improved when the data have a low signal-to-noise ratio.