Causalis

Evaluate the impact of the treatment on the outcome metric within the sample population, while controlling for confounding factors, to inform resource allocation decisions.

Why Causalis?

RCT Inference:

Estimate effect in your AB test

Observational Data Inference:

Estimate effect on observational data

DML Inference Refutation:

Check assumptions and robustness of the inference

EDA for your Data:

Propensity score distribution, SMD, and other useful plots

Advanced DGP:

Data Generating Process with non-linear effects, unobserved confounding, target treatment rate calibration, Gaussian copula, heterogeneous treatment effects and more

Modern State-of-the-Art Casusal Inference:

Double Machine Learning Interactive Regression Model. Designed for capturing nonlinear effects

And of course, Easy to Use💚:

Design templates, Baseline notebooks, Colored refutation tests, Real World Examples are separated from deep theory

Installation

pip install causalis

or from github directly

pip install git+https://github.com/ioannmartynov/causalis.git

Explore Causalis

User Guide

Causal Inference with Causalis instructions

User Guide

Real World Examples

Applied Causalis to real world examples

Real World Examples

Research

Theory research with math and code

Research

References

DoubleML/doubleml-for-py