Correlation coefficient

There are different fields of economics in charge of empirically measuring (estimation, prediction and inference) those relationships between variables, this is done through the application of statistical and mathematical methods in charge of providing valuable and useful content for decision making. Next, we will explain what the correlation coefficient is and what it is for, as well as its importance in the money demand model.

➡What is the correlation coefficient? ✨

The correlation coefficient or also called Pearson's correlation coefficient is focused on quantitative variables (minimum interval scale), and refers to an index that allows to analyze the degree of covariation that exists between those variables that are linearly related. Correlation refers in itself to the numerical form that statistics can verify through the relationship of one or more variables, which are achieved by measuring the level of dependence of a variable with respect to another totally independent variable. According to statistics, the correlation coefficient has a linear measure character between two random variables that are quantitative.

➡What is the correlation coefficient for? ✨

The main objective of the correlation coefficient is to measure the correlation between two variables. And among the advantages for which the correlation coefficient stands out with respect to other forms of correlation measurement, it is the so-called covariance, do not forget that the results of the correlation coefficient are between -1 and +1, its simplicity being useful to compare different correlations in a more direct and simple way. If you analyze two random variables X and Y, related to a certain population, the relationship coefficient will be expressed with Pxy.

➡How is it interpreted? ✨

This usually varies in the interval [-1,1], The sign thus establishing the meaning of the relationship, and the interpretation of each result is interpreted as follows:

• If r is equal to 1, it means that it is a positive correlation, where the index reflects the total dependence between both two variables, this is called a direct relationship, where one of the variables increases while the other increases in constant proportion .
• If 0 <r <1 it means that a positive correlation is occurring.
• If r = 0 there is no linear relationship, although this does not mean that the variables are independent, since there may be non-linear relationships between both variables.
• If -1 <r <0 indicates that there is a negative correlation.
• If r = - 1 indicates a perfect negative correlation and a total dependence between both variables, this is known as an inverse relationship. It occurs when one variable increases, while the other instead decreases in proportion.

The correlation reflects the measure of association between variables, so if it is applied in probability and statistics, the correlation will allow you to know exactly the strength and direction of the linear relationship that occurs between two or more random variables.