Home » Futures and Options » An investor’s guide to the covariance of stocks

An investor’s guide to the covariance of stocks

Covariance is a very important concept in stock investing, showing the connection between the movements of various stocks. In basic terms, covariance measures to what extent the stock prices of two companies tend to move together – whether they rise and fall at the same time or move inversely. 

Knowing covariance is crucial for investors as it allows them to evaluate the diversity level in their portfolio and manage risk appropriately. Let us take a closer look at the meaning of covariance of stocks, its formula, calculation, and more.

What is covariance?

Covariance is a mathematical concept that describes the extent to which two different variables change in unison. It measures how closely two variables are linearly related.

Covariance is applicable in the stock market and can be used to explain the connection between two different stocks’ returns. When covariance is positive, it means that there is simultaneous movement of both stocks in the same direction.

That implies that whenever one stock performs well, so does another, and vice versa for performing poorly. On the other hand, negative covariance occurs when these two stocks move in opposite directions, one doing badly when the other does well.

In order to diversify their portfolios, investors sometimes rely on covariance. They select stocks with negative covariances as this has the effect of reducing risk because if one stock underperforms, then the other will probably outperform it.

Formula for covariance

The formula for calculating the covariance of 2 stocks involves taking the average of the products of the deviations of their returns from their respective means.

In more detail, for each pair of corresponding returns from the two stocks, you subtract the mean return of the respective stock from each return. Then, you multiply these two deviations together. 

You do this for all pairs of returns, sum up these products, and then divide by the number of pairs minus one (this is for a sample covariance; for a population covariance, you’d divide by the number of pairs). This gives you the covariance.

Here’s the formula for clarity:

Cov(X, Y) = Σ [(X_i – X̄) * (Y_i – Ȳ)] / n


  • X and Y represent the returns of the two stocks.
  • X̄ and Ȳ represent the respective means or averages of the returns of stocks X and Y.
  • X_i and Y_i represent individual returns of stocks X and Y.
  • n is the total number of observations.

The formula here tells you how the returns of two stocks move together. A positive covariance indicates that the two stock returns are likely to move in the same direction, while a negative covariance implies they move in opposite directions.

Now, let’s take a look at how to calculate covariance of a stock. Here are the Steps to calculate Covariance:

  • Find the mean of X and the mean of Y
  • For each data point, find the product of their differences from their respective means
  • Sum them all up
  • Divide by n-1 (for a sample) or n (for a population)

Remember, a positive covariance means the variables are positively related, while a negative covariance means the variables are inversely related. A covariance of 0 indicates that the variables are independent.

Types of covariance

Covariance can have both positive and negative values, and based on this, it has two types:

  • Positive Covariance: This occurs when two variables tend to increase or decrease together. For example, height and weight are often positively covariant because taller people often weigh more.
  • Negative Covariance: This occurs when one variable tends to increase when the other decreases. For example, the amount of time spent running on a treadmill (increasing) and weight (decreasing) could be negatively covariant.

In the context of statistics and probability theory, especially in Multivariate Analysis and Gaussian Mixture Models, there are four types of covariance matrices:

  • Full: This is the general case where each component of the Gaussian Mixture Model has its own unconstrained covariance matrix.
  • Tied: All components share the same general covariance matrix.
  • Diagonal: Each component has its diagonal covariance matrix, meaning variances can differ, but all covariances are zero.
  • Spherical: Each component has a single variance, implying that the covariance matrix is a scalar times the identity matrix.

Each type has its own use cases and is used based on the requirements of the data and the model.

Covariance vs. Variance

Covariance is like a cousin to variance, another statistical concept. Both of them help us understand how data points are spread out in a set. However, while variance looks at the spread along just one line, covariance checks out how two things are related to each other.

In finance, covariance is super useful. It helps us figure out how different investments behave together. If two assets have a positive covariance, they usually go up or down at the same time.

But if the covariance is negative, they tend to move in opposite directions. Investors often like to find assets with negative covariance because they can help balance out their investment risks.

Covariance vs. Correlation

Covariance and correlation, while both statistical measures, serve different purposes. Covariance gauges the directional relationship between two variables, whereas correlation quantifies the strength of that relationship. The correlation is typically represented by a correlation coefficient, which can vary from -1 to +1.

A correlation is deemed to be strong if the correlation coefficient is near +1 (indicating a strong positive relationship) or -1 (indicating a strong negative relationship). A coefficient near zero suggests a weak or negligible relationship between the two variables.


Knowing how the covariance formula of two stocks works is key to navigating the stock market. It helps you grasp the connection between different stocks, making it easier to manage risks and make informed choices.

Remember, diversifying your portfolio based on covariance analysis can lower risks and boost returns. If you’re eager to learn more about covariance and other investment strategies, StockGro is a great platform designed to help people like you make smarter investment decisions.


How does covariance help in stock investing?

Covariance helps investors understand the relationship between different stocks in their portfolios. By knowing how stocks move together, investors can diversify effectively and manage risk.

What does a high covariance between stocks mean?

A high covariance suggests that the stocks’ returns tend to move in the same direction. This can increase portfolio risk, as both stocks may suffer losses simultaneously.

Can covariance be negative?

Yes, covariance can be negative. A negative covariance indicates that the stocks’ returns move in opposite directions. This can be beneficial for diversification, as losses in one stock may be offset by gains in the other.

How is covariance calculated?

Covariance is calculated using a formula that involves the deviations of each stock’s returns from their respective means, multiplied together and averaged over a specific time period.

Is covariance the same as correlation?

While covariance and correlation both measure the relationship between two variables, covariance measures the extent and direction of the relationship, whereas correlation standardizes this measurement to a range between -1 and 1, making it easier to interpret.

Enjoyed reading this? Share it with your friends.

Post navigation

Leave a Comment

Leave a Reply

Your email address will not be published. Required fields are marked *