Correlation: Karl Pearson’s Coefficient of Correlation;

Spearman’s Rank Correlation

Correlation: Meaning and Types

Correlation

A statistical tool that helps in the study of the relationship between two
variables is known as Correlation. It also helps in understanding the economic
behaviour of the variables.

The previous statistical approaches you have studied such as central tendency
and dispersion are limited to analysing a single variable or statistical analysis
and 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. Correlation is a statistical technique for determining the
relationship between two variables.

Therefore in simple word Correlation is a SIMPLE statistical relationship.

Definitions of Correlation: According to English & English:

“Correlation is a relationship or dependence. It is the fact that two things or

variables are so related that change in one is accompanied by a corresponding or
parallel change in the other.”

According to Ferguson “Correlation is concerned with describing the degree of

relation between two variables.”

According to Guilford: “A coefficient of correlation is a single number that tells

us to what extent two things are related, to what extent variation in one go with
variations in the other.”
According to Lathrop: “Correlation is a joint relationship between two
variables.”

Significance of Correlation

1. It helps determine the degree of correlation between the two variables in a

single figure.

2. It makes understanding of economic behaviour easier and identifies

critical variables that are significant.

3. When two variables are correlated, the value of one variable can be
estimated using the value of the other. This is performed with the
regression coefficients.

4. In the business world, correlation helps in taking decisions. The

correlation helps in making predictions which helps in reducing
uncertainty. It is so because the predictions based on correlation are
probably reliable and close to reality.

Correlation can be classified based on various categories:

Based on the direction of change in the value of two variables, correlation

can be classified as:

1. Positive Correlation:

When two variables move in the same direction; i.e., when one increases the
other also increases and vice-versa, then such a relation is called a Positive
Correlation. For example, Relationship between the price and supply, income
and expenditure, height and weight, etc.
2. Negative Correlation:

When two variables move in opposite directions; i.e., when one increases the
other decreases, and vice-versa, then such a relation is called a Negative
Correlation. For example, the relationship between the price and demand,
temperature and sale of woollen garments, etc.

Based on the ratio of variations between the variables, correlation can be

classified as:

1. Linear Correlation:

When there is a constant change in the amount of one variable due to a change
in another variable, it is known as Linear Correlation. This term is used when
two variables change in the same ratio. If two variables that change in a fixed
proportion are displayed on graph paper, a straight- line will be used to
represent the relationship between them. As a result, it suggests a linear
relationship.
In the above graph, for every change in the variable X by 5 units there is a
change of 10 units in variable Y. The ratio of change of variables X and Y in the
above schedule is 1:2 and it remains the same, thus there is a linear relationship
between the variables.

2. Non-Linear (Curvilinear) Correlation:

When there is no constant change in the amount of one variable due to a change
in another variable, it is known as a Non-Linear Correlation. This term is used
when two variables do not change in the same ratio. This shows that it does not
form a straight-line relationship. For example, the production of grains would
not necessarily increase even if the use of fertilizers is doubled.
Based on the number of variables involved, correlation can be classified as:

1. Simple Correlation:

Simple correlation implies the study between the two variables only. For
example, the relationship between price and demand, and the relationship
between price and money supply.

2. Partial Correlation:

Partial correlation implies the study between the two variables keeping other
variables constant. For example, the production of wheat depends upon various
factors like rainfall, quality of manure, seeds, etc. But, if one studies the
relationship between wheat and the quality of seeds, keeping rainfall and
manure constant, then it is a partial correlation.

3. Multiple Correlation:

Multiple correlation implies the study between three or more three variables
simultaneously. The entire set of independent and dependent variables is studied
simultaneously. For example, the relationship between wheat output with the
quality of seeds and rainfall.

Degree of Correlation
The degree of correlation is measured through the coefficient of correlation. The
degree of correlation for the given variables can be expressed in the following
ways:

1. Perfect Correlation:

If the relationship between the two variables is in such a way that it varies in
equal proportion (increase or decrease) it is said to be perfectly correlated. This
can be of two types:

 Positive Correlation: When the proportional change in two variables is

in the same direction, it is said to be positively correlated. In this case, the
Coefficient of Correlation is shown as +1.

 Negative Correlation: When the proportional change in two variables is

in the opposite direction, it is said to be negatively correlated. In this case,
the Coefficient of Correlation is shown as -1.

2. Zero Correlation:

If there is no relation between two series or variables, it is said to have zero or

no correlation. It means that if one variable changes and it does not have any
impact on the other variable, then there is a lack of correlation between them. In
such cases, the Coefficient of Correlation will be 0.
Applicability of correlation in Geographical Studies Correlation is the most
appropriate of all statistical tools used for geographical studies. The subject
matter of geography is a region of diversities and regional analysis is considered
to be the best method of studying it.