How many times until a coincidence becomes a pattern? The case of yield curve inversions preceding recessions and the magical number 7

Let us say that a coincidence involving two events, where one seems to predict the other, happens a number of times. How many times until it can be considered not only a coincidence, but a statistically significant pattern? We propose a framework to answer this question. Using the framework, we find that the number of times required is 7. We illustrate the practical application of our framework in the context of a very important phenomenon: When the percentage difference between 10-year and 3-month U.S. Treasury yields falls below zero, a U.S. recession appears to occur within the next 18 months.

All of this is laid out in much more detail in the article linked below. In this article, we have established the minimum number of times required for the inversion-recession phenomenon to be deemed more than a coincidence, and rather a statistically significant pattern. That number is 7. Therefore, given that since 1970 we have observed 8 instances of the inversion-recession phenomenon, we can conclude that this not a coincidence, and that it is in fact a statistically significant pattern.

https://www.tandfonline.com/doi/full/10.1080/03610926.2023.2232908

The video below complements this post, by briefly addressing some of the issues discussed in the post.