Macroeconomic Random Forest
Python: Ryan Lucas and I just released a Python version of the Macro RF package. It has a few additional options like parallel computing and financial trading backtest functionalities. Check out the webpage for all the details you need.
R: There is a Macro RF R Package. Type the following in R to get started:
#install.packages('devtools')
library(devtools)
install_github("philgoucou/macrorf");
library(MacroRF)
?MRF #you get the menu and a simple example.
There are also other R examples on the package’s webpage .
The newest version also include the external prediction function “pred.given.mrf” which can be used to construct iterated (perhaps multivariate) forecasts. Email me for raw codes.
TVP via Ridge
There is a R package for 2-step Ridge Regression as used in the paper. Type the following in R to get started:
#install.packages('devtools')
library(devtools)
install_github("philgoucou/tvpridge");
library(TVPRidge)
?tvp.ridge #you get the menu and a simple example.
MARX
Small R code to compute MARX directly from a feature matrix X (say, FRED-MD).
MARSquake and Booging
There is a R Package for Booging and MARSquake. Type the following in R to get started:
#install.packages('devtools')
library(devtools)
install_github("philgoucou/bagofprunes");
library(bagofprunes)
Try "?Booging" and "?MARSquake" for more info and easy examples.
VARCTIC
The 18 series of VARCTIC 18 are here. Please cite this if you use the data.
Can ML catch COVID?
The large UK data set, updated on a monthly basis, is available here.
On Spurious Causality, CO2, and GT
Data is available from Max Göbel’s website.