Correlation Analysis – Detailed Notes
Correlation analysis is a statistical technique used to measure the strength and
direction of the relationship between two or more variables. It helps in determining
whether and how strongly pairs of variables are related. In management, it is used
to identify relationships among factors such as sales and advertising, price and
demand, or income and expenditure.
Meaning and Definition
The term ‘correlation’ refers to the degree of association between two quantitative
variables. If the variables change together in a predictable pattern, they are said to
be correlated.
According to Ya-Lun-Chou: “Correlation analysis deals with the association
between two or more variables.”
Types of Correlation
1. Positive Correlation: When both variables move in the same direction (e.g.,
increase in income leads to increase in expenditure).
2. Negative Correlation: When one variable increases while the other decreases
(e.g., increase in price leads to decrease in demand).
3. Zero Correlation: When there is no relationship between the two variables.
4. Linear Correlation: When the relationship between variables can be
represented by a straight line.
5. Non-Linear Correlation: When the relationship is not constant and cannot be
represented by a straight line.
Methods of Studying Correlation
1. Scatter Diagram Method:
A graphical method that shows the relationship between two variables by plotting
them on a graph. The pattern of plotted points indicates the type and degree of
correlation.
2. Karl Pearson’s Coefficient of Correlation (r):
A quantitative measure of linear relationship between two variables. It ranges from
-1 to +1.
Formula:
r = Σ[(X - X■)(Y - ■)] / √[Σ(X - X■)² * Σ(Y - ■)²]
- r = +1 → Perfect positive correlation
- r = -1 → Perfect negative correlation
- r = 0 → No correlation
3. Spearman’s Rank Correlation:
Used when the data are in ranks (ordinal scale). It measures the degree of
association between two ranked variables.
Formula:
r■ = 1 - (6Σd²) / [n(n² - 1)]
where d = difference between ranks of two variables, and n = number of pairs.
4. Concurrent Deviation Method:
A simpler method used when the number of observations is large, based on the
direction of changes in the variables.
Interpretation of Correlation Coefficient
The correlation coefficient (r) indicates both the direction and strength of
relationship:
- If r = +1 → Perfect positive correlation.
- If r = -1 → Perfect negative correlation.
- If r = 0 → No correlation.
Guideline for Strength of Correlation:
|r| between 0.00 – 0.25 → Very weak
|r| between 0.26 – 0.50 → Moderate
|r| between 0.51 – 0.75 → Strong
|r| between 0.76 – 1.00 → Very strong
Importance and Applications of Correlation Analysis
- Helps in identifying relationships between economic or business variables.
- Useful in forecasting and planning (e.g., sales forecasting based on advertising
expenditure).
- Assists in testing the validity of assumed relationships in research.
- Supports decision-making in management, finance, marketing, and economics.
- Aids in developing regression equations for prediction.
Limitations of Correlation Analysis
- Correlation does not imply causation.
- Sensitive to outliers and extreme values.
- Only measures linear relationships.
- Misinterpretation is possible if the data are not properly scaled or cleaned.
- Inapplicable to qualitative variables without quantification.
Relationship between Correlation and Regression
- Correlation measures the strength and direction of a relationship.
- Regression quantifies the relationship and enables prediction.
- A high correlation (close to +1 or -1) indicates that regression will give reliable
predictions.
- When r = 0, regression coefficients are also zero.