Correlation seems almost like a magical word. In fact, most people don’t have to use this term more often than a couple of times a year.
In the world of investing, however, correlation is an important concept which has to do with how different assets move in relation to one another. Before we even dive into what correlation means in the world of statistics, we’ll focus on the intuition behind it.
Investing in gold and silver, mining stocks or other precious metals usually has the goal of earning a positive return. This is usually done by taking a position in an asset. For instance, an investor buys gold in hope of the appreciation of the yellow metal. If the price of gold goes up, there is a gain. If it goes down, there is a loss. All this is very simple but the purpose of this example is to show that the price fluctuations are very important to precious metals investors and traders.
The price of gold is one of the most important figures precious metals investors look at. But gold is not the only asset in the precious metals market. Silver and mining stocks are also very important. How do they relate to one another? Do gold and silver move in the same direction? Is the relationship stable? Maybe the relationship is different for different time horizons?
There’s more. The exchange rate of the U.S. dollar is one of the most important economic indicators for the U.S.-based precious metals investors. The largest mining stocks are quoted on stock exchanges. Is there a relationship between the miners and general stock market indices such as the Standard and Poor’s 500 (S&P 500)?
Now, the relationships we’re writing about can be either positive or negative. Positive in the sense that an increase in one indicator coincides with an increase in another. For instance, an increase in the price of gold might coincide with an increase in the price of silver. It can also be negative. For instance, an increase in the exchange rate of the U.S. dollar might coincide with a decrease in the price of gold priced in the dollar.
How to measure the sort of relationships we’re writing about? Correlation provides a way to quantify this. It puts a number on the relationship. This number ranges from -1 to 1 where the most negative number (-1) corresponds to a perfectly negative relationship (when one quantity goes up, the other goes down), while the most positive number (1) corresponds to a perfectly positive relationship (when one quantity goes up, the other goes up as well).
Of course, the real world is not perfect, meaning that the correlation almost never is exactly -1 or 1. Instead, it is usually a number somewhere in between. The closer the number to -1, the stronger and more negative the relationship used to be in the past. The closer the number to 1, the stronger and positive the relationship used to be in the past. There is also a third “special” number here, namely 0, the midpoint of the range. The closer the correlation is to 0, the weaker any kind of past relationship is. When the number is close to 0, we might say that there has been no correlation between the two quantities.
How might this be of use to precious metals investors? Let’s take a look at the correlations in the first week of August 2015 to see what they might tell us. We will do this by looking at the Correlation Matrix – our tool which calculates the correlations in the precious metals market and presents them in an easy-to-digest form.
A couple of words of introduction to the tool are in order here. The column on the left-hand side shows you the pairs of assets that the correlations have been calculated for. For instance, in the first row below the header of the table, we have “Gold / Silver.” This means that this row shows the correlations calculated between gold and silver. The second row is labeled “Gold / USD.” This denotes the correlation between gold and the U.S. dollar. As such, the second row displays correlations between gold and the greenback.
Now, you have probably noticed that each row displays various correlations, not just one number. The different numbers show you the correlation over a given number of days, from 10 to 1500 (10 and 30 are marked as short-term, 90 and 250 as medium-term, 750 and 1500 as long-term). These different numbers of days are organized in columns (10, 30, 90 and so on).
Putting the rows together with the columns gives you specific correlations. For example, the number in the “Gold / Silver” row, in the 1500 column is 0.89. This means that the correlation between gold and silver over the last 1500 days was 0.89. If you look at the “Gold / S&P” row and the 10 column, you see -0.27. This means that the correlation between gold and the S&P 500 index over the past 10 days stood at -0.27.
To make things easier for you, we have marked the correlations with arrows – green, red and yellow. Green arrows show you potentially strong positive correlation, red ones potentially strong negative correlation while yellow indicate that the correlation might be moderate (in either direction). The easiest way to read this is that a green arrow shows you that the two assets (indices) tended to move in the same direction, a red that the assets tended to move in opposite directions while a yellow one that the assets tended to fluctuate rather independently.