A Bayesian Model Comparison for Trend-Cycle Decompositions of Output
This code estimates the output gaps from six unobserved components models using US GDP data.
The code also computes the marginal likelihood for each model using the improved cross-entropy method developed in Chan and Eisenstat (2015).
The six unobserved components models are:
- UC model with orthogonal trend and cycle innovations
- UC model with correlated trend and cycle innovations
- correlated UC model with one break in trend output growth
- correlated UC model with two breaks in trend output growth
- UC model with a deterministic trend output
- UC model with a deterministic trend output and one break