Posts

Synthetic Control
INTRO Self-Driving Cars Suppose you were a ride-sharing platform and you want to test the effect of self-driving cars in your fleet. As you can imagine, there are many limitations to running an AB/test for this type of feature.
Jul 10, 2023 14 min read
Synthetic Control
The Bayesian Bootstrap
A short guide to a simple and powerful alternative to the bootstrap In causal inference we do not want just to compute treatment effect, we also want to do inference (duh!
Jul 10, 2023 10 min read
The Bayesian Bootstrap
The FWL Theorem, Or How To Make All Regressions Intuitive
An introduction to the Frisch-Waugh-Lowell theorem and how to use it to gain intuition in linear regressions The Frisch-Waugh-Lowell theorem is a simple but yet powerful theorem that allows us to reduce multivariate regressions to univariate ones.
Jul 10, 2023 10 min read
The FWL Theorem, Or How To Make All Regressions Intuitive
Understanding AIPW
An introduction to doubly-robust estimation of conditional average treatment effects (CATE) When estimating causal effects, the gold standard is randomized controlled trials or AB tests. By randomly exposing units to a treatment we make sure that individuals in both groups are comparable, on average, and any difference we observe can be attributed to the treatment effect alone.
Jul 10, 2023 17 min read
Understanding AIPW
Understanding Causal Trees
How to use regression trees to estimate heterogeneous treatment effects. In causal inference we are usually interested in estimating the causal effect of a treatment (a drug, ad, product, …) on an outcome of interest (a disease, firm revenue, customer satisfaction, …).
Jul 10, 2023 16 min read
Understanding Causal Trees
Understanding Contamination Bias
Problems and solutions of linear regression with multiple treatments In many causal inference settings, we might be interested in the effect of not just one treatment, but many mutually exclusive treatments.
Jul 10, 2023 14 min read
Understanding Contamination Bias
Understanding Meta Learners
How to use machine learning to estimate heterogeneous treatment effects In many settings, we are not just interested in understanding a causal effect, but also whether this effect is different for different users.
Jul 10, 2023 12 min read
Understanding Meta Learners
Weighting, Matching, or Regression?
Understanding and comparing different methods for conditional causal inference analysis AB tests or randomized controlled trials are the gold standard in causal inference. By randomly exposing units to a treatment we make sure that individuals in both groups are comparable, on average, and any difference we observe can be attributed to the treatment effect alone.
Jul 10, 2023 17 min read
Weighting, Matching, or Regression?
Understanding The Chi-Squared Test
If you search the Wikipedia definition of Chi-Squared test, you get the following definition: Pearson’s chi-squared test $\chi^2$ is a statistical test applied to sets of categorical data to evaluate how likely it is that any observed difference between the sets arose by chance.
May 31, 2022 12 min read
Understanding The Chi-Squared Test
How To Make A Personal Website with Hugo
Introduction During the second year of my PhD, I decided that I wanted to have a personal website. After (too many) hours of research, I decided to build it using Hugo, and I picked the Wowchemy theme, also known as Hugo Academic.
Apr 18, 2022 9 min read
How To Make A Personal Website with Hugo