FARS - Factor-Augmented Regression Scenarios

The FARS package provides a comprehensive framework in R for modeling and forecasting economic scenarios based on the multi-level dynamic factor model (MLDFM). The package enables users to:

• 1. Extract global and group-specific factors using a flexible multi-level factor structure.
• 2. Compute asymptotically valid confidence regions for the estimated factors, accounting for uncertainty in the factor loading.
• 3. Obtain estimates of the parameters of the factor-augmented quantile regressions together with their standard deviations.
• 4. Recover full predictive conditional densities from estimated quantiles.
• 22. Obtain risk measures based on extreme quantiles of the conditional densities.
• 6. estimate the conditional density and the corresponding extreme quantiles when the factors are stressed.

Installation and Usage

For detailed usage and examples please refer to the FARS Vignette. The Vignette llustrates the functionalities of the FARS package by extracting factors, estimating conditional densities, and constructing stressed scenarios in two applications:

• 1. Aggregate inflation in Europe
• 2. Building growth density scenarios for the United States (replicating González-Rivera, G., Rodríguez-Caballero, C. V., & Ruiz, E., 2024. Expecting the unexpected: Stressed scenarios for economic growth. Journal of Applied Econometrics, 39(5), 926–942. https://doi.org/10.1002/jae.3060)