Many of you may have seen a graph similar to the one below - which highlights the similarity between these series. 🔎 But is it possible to use M2 to PREDICT future BTC movements?

We can use the Granger Causality Test to seek an answer with quantitative basis. 📏

Despite the name, it is worth mentioning that the test does not measure structural or economic causality per se, but rather temporal precedence with predictive power.

In other words, whether one series can be used to predict the other.

The test returns a p-value. When it is less than 0.05, we can say that there is some predictive power (with a statistical margin of error).

We tested for M2 -> BTC, varying some parameters.

The results indicate that there is no stable or continuous relationship between variations in M2 and BTC performance.

But at some points, the test returns a statistically significant value - indicating that, in these periods, M2 can help in analyzing BTC prices.

These periods appear to coincide with certain monetary policy dynamics.

In the full research, we explore this behavior further.

We detail the methodology used and how the metrics work, discuss our results and highlight the main insights.