Michael J. Lee

Hello!

I'm a research scientist at the MIT Siegel Family Quest for Intelligence, where I work on building tools for collecting human behavior.

Before that, I received a PhD in cognitive science (also at MIT). I went to Duke for undergrad, where I studied electrical & biomedical engineering.

Recent posts

All posts

Estimating noise ceilings for the Pearson correlation coefficient

In this post, I derive a commonly used split-half estimator for correlational noise ceilings. This involves a detour through classical test theory and the Spearman-Brown prediction formula.

Factor analysis through the lens of prediction

Factor analysis is a classical statistical method underlying some of the most important results in psychology. In this blog post, I study it through the lens of prediction.