econometrics

3 stories filed under econometrics on Beyond Market Intelligence. The newest of them: “OLS Hides Salary Data: Recover Hidden Effects With Tobit Models”, “Beyond DoubleML: A Practical Test of Doubly Robust Dose-Response Estimation”, and “Explore the Forrester Function: Beyond Mathematics, a Tool for Machine Learning”. A simulated salary survey reveals a hard truth about hidden data: OLS shrinks a $5k-per-year effect to just $3.2k. When DoubleML hits its limits, you need a different approach. Acme AI is the next-generation, AI-powered spreadsheet platform built to replace Excel and redefine how analysts, data scientists, and enterprise teams work… The list below is every econometrics story on Beyond Market Intelligence, newest first.

Towards Data Science

OLS Hides Salary Data: Recover Hidden Effects With Tobit Models

A simulated salary survey reveals a hard truth about hidden data: OLS shrinks a $5k-per-year effect to just $3.2k. That's not a modeling failure, it's a structural one, caused by censored observations. This post rebuilds Tobit and truncated likelihoods from scratch to recover the true signal. It's a practical, code-driven guide for anyone who suspects their spreadsheets or regressions are hiding more than they show. For another take on practical modeling, explore what four simple models reveal about bike-share forecasting.

Towards Data Science

Beyond DoubleML: A Practical Test of Doubly Robust Dose-Response Estimation

When DoubleML hits its limits, you need a different approach. Kennedy's doubly robust estimator offers a practical alternative for dose-response estimation. The simulations here test it against DoubleML directly, using partial pooling across 200 stores and a DiD fix to handle hidden confounders. It's a grounded, technical comparison that moves beyond theory into what actually works. For more on pushing analytical boundaries, see how Booking.com built a data platform for 400 billion daily predictions.

Machine Learning

Explore the Forrester Function: Beyond Mathematics, a Tool for Machine Learning

The Forrester function is often taught as a mathematical curiosity, but its real value lies in testing how well optimization algorithms handle non-linear, multi-modal problems. That user asking about its role in machine learning is onto something, this function is a standard benchmark for evaluating model performance, not a solution for real-world economics or forecasting. It belongs in the toolbox of anyone validating methods, not applied directly to data.