Correlation Study

By Samantha Baltodano

TL;DR:

The Correlation study assesses whether two financial securities have a linear relationship with each other. The correlation coefficient is calculated and varies on a scale of -1 to +1. A -1 value indicates a perfect negative relationship. A +1 value indicates a perfect negative relationship. Meanwhile, a correlation coefficient of 0 suggests there is no linear relationship between two securities.

What Is the Correlation Study?

The Correlation study calculates the correlation coefficient between one security and another security or index. The correlation coefficient is a statistical measure of the strength of a linear relationship between two variables, in this case two financial securities. 

Correlation coefficient values range on a -1 to +1 scale. 

Source: iStock

Figure 1: Correlation coefficients expressed graphically

A correlation coefficient equal to +1 suggests perfect positive correlation. This means that there is a direct relationship between the two securities. If the price of security A increases, then security B’s price will also increase to an equal degree. Likewise, if the price of security A decreases, then the price of security B also decreases to an equal degree.

The perfect inverse, or negative, correlation is represented by a coefficient of -1. This means that as the price of security A increases, the price of security B decreases to an equal degree. If the price of security A decreases, then the price of security B increases to an equal degree.

When prices move independently, the correlation coefficient is 0. This signifies that there is no linear correlation between the price of two securities.

–

Perfect positive and perfect negative correlations are rare in the wild, but you can find strong positive and negative correlations in day to day items.

For example, let’s consider temperature and ice cream:

A nice, cold ice cream cone on a hot summer day sounds like the perfect treat. A nice cold ice cream cone when you’re stuck in a snowstorm? That’s probably not your first choice. 

In this way, temperature and ice cream have a strong positive correlation. As temperature rises, so do ice cream sales and vice versa.

On the opposite end of the spectrum, let’s consider time spent running and body fat:

When you run more, it’s likely that your body fat will decrease. If you never run, it’s likely you might have a high body fat.

As time spent running increases, body fat decreases and vice versa. This indicates a strong negative correlation. The two variables have an inverse linear relationship.

Let’s also consider coffee consumption and intelligence:

In this case, these two variables really don’t impact one another. There’s no evidence that an increase in coffee consumption will make you smarter or dumber. So, there is no correlation between the two items.

–

Correlation Statistics and Investing

The correlation coefficient is especially helpful in assessing and managing investment risks. For example, modern portfolio theory suggests diversification can reduce the volatility of a portfolio's returns, curbing risk. 

The correlation coefficient between historical returns can indicate whether adding an investment to a portfolio will improve its diversification.

Meanwhile, quantitative traders use historical correlations and correlation coefficients to anticipate near-term changes in securities prices.

Summary

• Correlation coefficients are used to gauge the relationship between two securities.
• Values range from -1 for a perfectly inverse, or negative, relationship to +1 for a perfectly positive correlation. Values at or near 0 indicate no linear relationship between securities.
• Correlation coefficients can be used on historical price data to determine if adding a particular security to your portfolio improves overall diversification of the portfolio.

Correlation is just one of many studies that Archaide automates. For a full list of strategies and studies available click here.

Like what you read? Check out the rest of our content!