My Latest Post

There is a new post on my blog on causal inference techniques for business analytics! This post is even more spruced up than my post on propensity score matching! In this post I provide an in-depth explanation of heterogeneous treatment effects which measure the extent of causal effects for different subsets of an observed population. In this post, I present a variety of methodologies for estimating varied causal effects amongst observed individuals with varied characteristics, describe how heterogeneous treatment effects can be leveraged to build effective digital marketing campaigns, and present a few more interactive visualizations to illustrate the mathematical concepts I discuss. Be sure to check it out!

Click To See My Latest Post!

In a previous blog post, I presented a methodology for quantifying causal effects by estimating average treatment effects, or the average of all effects a particular treatment has on a population of observed individuals. Estimating an average treatment effect can help an analyst understand the population level effect of a particular intervention or policy and can enable the calculation of aggregated metrics, such as an expected increase in revenue as a result of a new ad campaign or the expected result of a life-saving experimental drug. However, an analyst is often not solely interested in aggregated causal effects, but is rather interested in understanding the effect a policy will have on a particular individual given a set of their definitive characteristics which may or may not influence their reaction to a particular intervention. Heterogeneous treatment effect estimation is a powerful strategy for identifying these differential effects, and in this post I discuss how it can be used to help digital marketers optimally target a subset of accessible consumers in order to maximize their marketing ROI.