Examples Gallery#
This gallery showcases various examples demonstrating the capabilities of CausalLib. Each example is a Jupyter notebook that you can view, download, and run locally.
Models and Features#
Inverse probability weighting is a basic model to obtain average effect estimation.
Also known as standardization
Basically, different ensemble models that utilize a weight model to augment the outcome model.
Targeted learning is a method developed by Mark van der Laan [1] establishing…
R-Learner provides a general framework for estimating causal effects using Machine Learning (ML) algorithms.
X-learner is a Meta-algorithm by künzel et al. (2018)
The modules under causallib.estimation estimate treatment effect on outcomes that are measured at a particular time point (e.g., effect of smokin…
To find the expected effect of the intervention on the population, we match each treated individual with one or more untreated individuals which ar…
When performing matching on a sample set, we may want to use non-standard distance measurements or faster implementations. The default behavior is …
Economists have long-hypothesized that training programs could improve the labor market prospects of participants.
This Notebooks presents several models that perform overlap exclusion
causallib evaluation plotsTo make it easier to assess the quality of the causal models, causallib supplies a number of evaluation plots.
Real-World Use Cases#
In this example we will perform a quick causal analysis to estimate the causal effect of smoking cessation on weight gain over a period of a decade.
Economists have long-hypothesized that training programs could improve the labor market prospects of participants.
NHANS (National Health and Nutrition Examionation Survey) Epidemiologic Followup Study
We will use the Measured Annual Nutrient loads from AGricultural Environments (MANAGE) data from the USDA,
We look at the famous Card and Krueger study[1] of the impact of a minimum wage change on employment levels in fast food restaurants near the borde…
Economists have long-hypothesized that training programs could improve the labor market prospects of participants.
Consider the case when input data already exists, and that data already has a causal structure.