This work aims to present a full Bayesian framework to identify, extract and forecast unobserved components in time series. The major novelty is to present a probabilistic framework to analyze the identification conditions. More precisely, informative prior distributions are assigned to the spectral densities of the unobserved components. This entails a… (More)

Figure 7: Prior (dotted line) and posterior (solid line) distributions of the normalization parameter τY for sunspot data. The hyper-parameters are equal to K = 120, M = 1, vY = 10, v ∗ Y = 10,τ̃Y = σ̂ 2 Y /2π and the number of iterations is N = 60000.