Boosting High Dimensional Predictive Regressions with Time Varying Parameters

In an extensive application to macroeconomic forecasting with many potential predictors, we find that the benefits to modeling time variation are substantial and they increase with the forecast horizon. Furthermore, the timing of the benefits suggests that the Great Moderation is associated with substantial instability in the conditional mean of various economic series. This zip file contains replication instructions along with the following four folders: 1) Final Data: Contains all the processed data.

We also formed our response for each of the horizons and have them as separate csv files. Data source: 2) Create Response: Contains the code and the files needed to create our response variables for each of our horizons. The results from this code is contained in the final data folder. 3) Simulations: Contains the code for the simulations section 4) MacroForecasting Code: Most of the code is contained in this folder