ValidMLInference 1.0.7

This package implements bias correction methods for models estimated using synthetic data

ValidMLInference

ValidMLInference is a Python package for estimating linear models which use synthetically generated regressors. The bias-correction methods are described in Battaglia, Christensen, Hansen & Sacher (2024).

Requirements and installation

ValidMLInference runs on Python 3.8 and requires a couple of standard numerical packages: numpy, scipy, jax, jaxopt, and numdifftools.You can install ValidMLInference by typing > pip install ValidMLInference into the terminal.

Using ValidMLInference

To get started with using the package, we recommend looking at the following examples and resources: - remote_work.ipynb this notebook contains an example of estimating the association between working from home and salaries in job postings using real-world data - synthetic_example.ipynb this notebook contains an example showing the performance of the different estimators on synthetic data - functionality.md this file contains descriptions of the functions, optional arguments, etc.