Why High Correlation Does Not Establish Futures Cointegration

Summary

The document raises a question about soybean and soybean meal futures, which the author describes as highly correlated because they share an underlying agricultural market. A linear regression between the two series produces residuals that fail an Augmented Dickey–Fuller stationarity test. The author asks whether this result means the apparent relationship is spurious, despite the strong correlation.

The post supplies no answer, test output, data period, or model specification, so it does not establish whether these contracts are cointegrated. Its research question highlights a useful distinction: correlation measures co-movement, while cointegration concerns whether a combination of nonstationary price series has a stationary long-run spread. ADF residual testing can inform that assessment, but conclusions depend on implementation and assumptions. The document is therefore a prompt for further analysis rather than evidence for a trading strategy or a resolved finding.

Key ideas

• High correlation between two futures series does not by itself establish cointegration.
• The author tests regression residuals for stationarity with an Augmented Dickey–Fuller test.
• The reported residual test fails to support cointegration in the examined setup.
• The document lacks details needed to evaluate the data, regression, or test result.

Tags

# Spurious regression between two futures with the same underlying highly correlated (cor=0.9)


# Spurious regression between two futures with the same underlying highly correlated (cor=0.9)












analyzing the correlation between soybean and soybean meal futures in ECBOT, and making a linear regression in R between them I check with an ADF Test that the residuals are not stationary, so theoretically both series are not cointegrated, else they have a spurious relationship. But, has this sense? They are over the same underlying and highly correlated (not like Soybean Oil and Soybean futures that have poor correlation).

Cheers, Gonzalo.

Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.