Matlab code for the BMIDAS models proposed in Kohns & Potagailo (2023) "Flexible Bayesian MIDAS: time‑variation, group‑shrinkage and sparsity", a working paper version can be found here. The code runs the nowcasting exercise for UK GDP growth using the BMIDAS model with GIGG prior and ex-post sparsification. It also incorporates alternative versions of the model without time-varying components or without sparsification step. The paper is currently in round 2 of revisions at Journal of Business and Economic Statistics.
If you use the code in your work please cite as:
Kohns, D., & Potjagailo, G. (2023). Flexible Bayesian MIDAS: time‑variation, group‑shrinkage and sparsity. Bank of England Working Paper.
This site it currently undergiong revisions in line with the review process at JBES. The new branch will soon be merged into main.