Published in Towards Data Science·Feb 20From Causal Trees to ForestsHow to use random forests to do policy targeting — In my previous blog post, we have seen how to use causal trees to estimate the heterogeneous treatment effects of a policy. If you haven’t read it, I recommend reading that first since we will take that article's content for granted and start from there. Why heterogenous treatment effects (HTE)…Data Science13 min readData Science13 min read
Published in Towards Data Science·Feb 3Understanding Causal TreesHow 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, …). However, knowing that a treatment works on average is often not sufficient and we would like to know…Statistics15 min readStatistics15 min read
Published in Towards Data Science·Jan 10Bayesian AB TestingUsing and choosing priors in randomized experiments. — Randomized experiments, a.k.a. AB tests, are the established standard in the industry to estimate causal effects. Randomly assigning the treatment (new product, feature, UI, …) to a subset of the population (users, patients, customers, …) we ensure that, on average, the difference in outcomes (revenue, visits, clicks, …) can be…Data Science11 min readData Science11 min read
Jan 3Free Causal Inference ResourcesA regularly updated collection of free resources to approach, explore and master causal inference topics — Since I have been asked many times for suggestions and resources to approach the field of causal inference, I decided to collect in this article what I personally think are the best free resources available online to either approach the field or expand your knowledge. I will try to suggest…Causal Inference7 min readCausal Inference7 min read
Published in Towards Data Science·Dec 29, 2022Experiments on Returns on InvestmentAn introduction to the delta method for inference on ratio metrics. — When we run an experiment, we are often not only interested in the effect of a treatment (new product, new feature, new interface, …) on revenue, but in its cost-effectiveness. In other words, is the investment worth the cost? Common examples include investments in computing resources, returns on advertisement, but…Causal Data Science13 min readCausal Data Science13 min read
Published in Towards Data Science·Oct 10, 2022Mean vs Median Causal EffectAn introduction to quantile regression in A/B tests — In A/B tests, a.k.a. randomized controlled trials, we usually estimate the average treatment effect (ATE): the effect of a treatment (a drug, ad, product, …) on an outcome of interest (a disease, firm revenue, customer satisfaction, …), where the “average” is taken over the test subjects (patients, users, customers, …)…Statistics11 min readStatistics11 min read
Published in Towards Data Science·Sep 8, 2022A/B Tests, Privacy, and Online RegressionHow to run experiments without storing individual-level data — AB tests, a.k.a. randomized controlled trials, are widely recognized as the gold standard technique to compute the causal effect of a treatment (a drug, ad, product, …) on an outcome of interest (a disease, firm revenue, customer satisfaction, …). The procedure consists in randomly splitting a set of subjects (patients…Causal Inference8 min readCausal Inference8 min read
Published in Towards Data Science·Aug 17, 2022Outliers, Leverage, Residuals, and Influential ObservationsWhat makes an observation “unusual”? — In data science, a common task is anomaly detection, i.e. understanding whether an observation is “unusual”. First of all, what does it mean to be unusual? In this article we are going to inspect three different ways in which an observation can be unusual: it can have unusual characteristics, it…Causal Inference8 min readCausal Inference8 min read
Published in Towards Data Science·Aug 8, 2022The Bayesian BootstrapA short guide to a simple and powerful extension of the bootstrap — In causal inference we do not want just to compute treatment effects, we also want to do inference. Understanding the uncertainty surrounding a point estimate is often much more informative and valuable than the point itself. In some cases, it’s very easy to compute the (asymptotic) distribution of an estimator…Causal Inference9 min readCausal Inference9 min read
Published in Towards Data Science·Jul 30, 2022Understanding Synthetic Control MethodsA detailed guide to one of the most popular causal inference techniques in the industry — It is now widely accepted that the gold standard technique to compute the causal effect of a treatment (a drug, ad, product, …) on an outcome of interest (a disease, firm revenue, customer satisfaction, …) is AB testing, a.k.a. randomized experiments. We randomly split a set of subjects (patients, users…Causal Inference15 min readCausal Inference15 min read
