Correlation and Causation

The degree of correlation between two or more variables can be determined using correlation. However, it does not consider the cause-and-effect relationship between variables. If two variables are correlated, it could be for any of the following reasons:

1. Third-Party Influence:

The influence of a third party can result in a high degree of correlation between the two variables. This analysis does not take into account third-party influence. For example, the correlation between the yield per acre of grain and jute can be of a high degree because both are linked to the amount of rainfall. However, in reality, both these variables do not have any effect on each other.

2. Mutual Dependence (Cause and Effect):

It may be challenging to determine which is the cause, and which is the effect when two variables indicate a high degree of correlation. It is so because they may be having an impact on one another. For example, when there is an increase in the price of a commodity, it increases its demand. Here, the price is the cause, and demand is the effect. However, there is a possibility that the price of the commodity will rise due to increased demand (population growth or other factors). In that case, increased demand is the cause, and the price is the effect.

3. Pure Chance: 

It is possible that the correlation between the two variables was obtained by random chance or coincidence alone. This correlation is also known as spurious. Therefore, it is crucial to determine whether there is a possibility of a relationship between the variables under analysis. For example, even if there is no relationship between the two variables (between the income of people in a society and their clothes size), one may see a strong correlation between them.

So, it can be said that correlation provides only a quantitative measure and does not indicates cause and effect relationship between the variables. For that reason, it must be ensured that variables are correctly selected for the correlation analysis.

The previous statistical approaches (such as central tendency and dispersion) are limited to analysing a single variable or statistical analysis. This type of statistical analysis in which one variable is involved is known as Univariate Distribution. However, there are instances in real-world situations where distributions have two variables like data related to income and expenditure, prices and demand, height and weight, etc. The distribution with two variables is referred to as Bivariate Distribution. It is necessary to uncover relationships between two or more statistical series. Correlation is a statistical technique for determining the relationship between two variables.

According to L.R. Connor, “If two or more quantities vary in sympathy so that movements in one tend to be accompanied by corresponding movements in others, then they are said to be correlated.”

In the words of Croxton and Cowden, “When the relationship is of a quantitative nature, the appropriate statistical tool for discovering and measuring the relationship and expressing it in a brief formula is known as correlation.”

According to A.M. Tuttle, “Correlation is an analysis of covariation between two or more variables.”