Non-parametric generalized differences-in-differences estimation, with covariate matching.
TSCSMethods works on a standard computer, with sufficient RAM and processing power to support the size of the dataset analyzed by the user. This will be a computer with at least 16 GB, and 4 cores.
The package was tested on a computer with 64 GB of RAM, 16 cores @ 3.4Ghz.
This package was tested on on MAC OSX 17.0. All of the underlying dependencies are compatible with Windows, Mac, and Linux systems.
This package has been tested on Julia 1.7.1.
Julia may be installed on Mac OSX using homebrew https://brew.sh by executing:
brew install juliaOtherwise, consult the Julia Language website for installation on your system https://julialang.org/downloads/.
Users should install the following packages prior to installing TSCSMethods, from within a julia session:
pkgs = ["Random", "DataFrames", "Dates", "CSV", "JLD2"]
import Pkg
for pkg in pkgs; Pkg.add(pkg) end
which will install in less than 5 minutes with the recommended specs.
The TSCSMethods package functions with all packages in their latest versions as they appear on CRAN on March 08, 2022. The versions of all Julia package dependencies (for TSCSMethods) may be found in the "Manifest.toml" file, and are installed with the package automatically.
From within a julia session, type:
import Pkg; Pkg.add("https://github.com/human-nature-lab/TSCSMethods.jl")
The package should take approximately 1 minute to install.
See vignette.ipynb in the vignette directory for a simple analysis example as a Jupyter notebook.
For usage of the package and associated manuscript, please cite as:
TSCSMethods