Business Statistics CS GUPTA BOOK PDF

Limitations/precautions of correlation:

1. Correlation does not indicate causation.
2. Pearson’s r measures linear relationship only; r=0 may still have non-linear relation.
3. Extreme values and mixed data can mislead correlation results.

(Any three points can be written.)

Range merits/demerits:

Merits:

1. Very simple and quick to compute.
2. Useful for rough comparison.

Demerits: 3) Depends only on extreme values and ignores the rest.

(Any three points can be written.)

Karl Pearson’s coefficient of correlation (r) measures the strength and direction of linear relationship between two variables.

Important points:

• r lies between -1 and +1.
• r > 0: positive correlation; r < 0: negative correlation.
• |r| close to 1 indicates strong correlation; |r| close to 0 indicates weak correlation.

Therefore, Pearson’s r is very useful for measuring linear association, but it should be interpreted carefully because correlation does not prove causation.