- Foundation
- About 16 min
- 5 practice questions
Scatter diagrams
Use a scatter diagram to judge the presence, direction and closeness of a relationship, recognise perfect, zero and non-linear patterns, and know the three tools for studying correlation.
If something looks wrong, please tell us.
By the end of this lesson you can
- Name the three techniques for studying correlation.
- Describe how a scatter diagram is drawn and read.
- Identify positive, negative, perfect, no correlation and non-linear patterns from described points.
The chapter studies three tools: the scatter diagram, Karl Pearson's coefficient of correlation and Spearman's rank correlation. The scatter diagram gives a visual picture without any number; Karl Pearson's coefficient gives a number for the linear relationship between two measured variables; Spearman's coefficient measures the linear association between ranks, useful for attributes that cannot be measured, such as honesty or intelligence.
Drawing a scatter diagram
Plot each pair of values (X, Y) as a point on graph paper, with X on the horizontal axis and Y on the vertical axis. Do not join the points. The overall direction of the points and their closeness to a line show the nature and intensity of the relationship.
| Pattern of points | What it shows |
|---|---|
| Scattered around an upward-rising line | Positive correlation: X up, Y up |
| Scattered around a downward-sloping line | Negative correlation: X up, Y down |
| No upward or downward line; points spread everywhere | No correlation |
| All points exactly on an upward-rising line | Perfect positive correlation (r = +1) |
| All points exactly on a downward-sloping line | Perfect negative correlation (r = −1) |
| Points close to a line | High (strong) correlation |
| Points widely dispersed around the line | Low (weak) correlation |
| Points along a curve (rising then flattening, or U-shaped) | Non-linear relationship |
A scatter diagram shows the nature of the relationship visually and is not confined to linear relations; it gives no numerical value. If all points lie on a line, the correlation is perfect.
Worked example 1: describing a scatter from data
Illustrative data for six made-up farms: fertiliser used (bags per acre) and yield (quintals per acre): (1, 12), (2, 15), (3, 15), (4, 19), (5, 20), (6, 24). Step 1, plot: points at these coordinates. Step 2, direction: as X goes from 1 to 6, Y goes from 12 to 24; the points climb from lower left to upper right. Step 3, closeness: the rises in Y are 3, 0, 4, 1, 4: not equal, so the points do not lie exactly on one line, but they stay close to an upward line. Conclusion: high positive correlation, but not perfect.
Worked example 2: perfect correlation
Illustrative: a made-up taxi charges a fixed ₹50 plus ₹15 per km. For 2, 4, 6 and 8 km, the fare is 50 + 15 × 2 = ₹80, ₹110, ₹140 and ₹170. Each extra 2 km adds exactly ₹30, so all four points lie on one upward straight line: perfect positive correlation. If instead a made-up stock of 100 kg of rice is reduced by 10 kg each day, the stock after 1, 2, 3, 4 days is 90, 80, 70, 60 kg: points on a downward straight line, perfect negative correlation.
Worked example 3: a non-linear pattern
Illustrative: X = −3, −2, −1, 1, 2, 3 and Y = X squared = 9, 4, 1, 1, 4, 9. The points fall and then rise in a U-shape. There is an exact relationship (Y is always X squared), but it is not linear: the left half slopes down and the right half slopes up, so they cancel and the linear correlation works out to zero. This is why it is advisable to look at the scatter diagram first before calculating Karl Pearson's coefficient, which measures only linear relationships.
Patterns seen in scatter diagrams
-
Linear
- Positive (upward line)
- Negative (downward line)
- Perfect positive or perfect negative (on the line)
-
No correlation
- Points with no upward or downward line
-
Non-linear
- Positive non-linear (rising curve)
- Negative non-linear (falling curve)
- U-shaped or other curves
Scatter diagram as a tool
-
Strengths
- Quick visual idea of direction and closeness
- Shows non-linear patterns too
- Helps decide whether r is appropriate
-
Limitations
- Gives no numerical value
- Judgement of 'high' or 'low' is rough
- Hard to compare two scatters precisely
Key takeaways: the three tools are the scatter diagram, Karl Pearson's r and Spearman's rank correlation. A scatter diagram plots pairs as points; upward drift means positive, downward means negative, no drift means none, points on a line mean perfect correlation, and a curve means a non-linear relation. Check the scatter before computing r.
Check your understanding
-
1. Which tool gives a visual idea of the relationship without any numerical value?
- Karl Pearson's coefficient
- Spearman's rank correlation
- Scatter diagram
- Covariance
Show answer
Answer: C. A scatter diagram plots the pairs of values as points; it shows direction and closeness visually but gives no number.
-
2. If all points of a scatter diagram lie on a downward-sloping straight line, the correlation is:
- perfect negative
- perfect positive
- zero
- low negative
Show answer
Answer: A. Points exactly on a line indicate perfect correlation; a downward slope makes it negative, so r = −1.
-
3. Points widely spread around an upward-rising line indicate:
- perfect positive correlation
- high negative correlation
- no relationship of any kind
- low positive correlation
Show answer
Answer: D. An upward drift means positive correlation; wide dispersion around the line means the correlation is low.
-
4. Illustrative: a shop charges ₹20 per notebook. For 1, 2, 3 and 4 notebooks the bills are ₹20, ₹40, ₹60 and ₹80. A scatter of quantity and bill would show:
- no correlation
- perfect positive correlation
- perfect negative correlation
- a non-linear relation
Show answer
Answer: B. Each extra notebook adds exactly ₹20, so all points lie on one upward straight line: perfect positive correlation.
-
5. Assertion (A): One should examine the scatter diagram before calculating Karl Pearson's coefficient. Reason (R): Karl Pearson's coefficient measures only linear relationships and can mislead when the relation is non-linear.
- Both A and R are true, and R is the correct explanation of A
- Both A and R are true, but R is not the correct explanation of A
- A is true, but R is false
- A is false, but R is true
Show answer
Answer: A. Both are true, and R explains A: the scatter shows whether the relation is linear; if it is curved, r would be misleading, so the scatter is checked first.
Sign in to keep track of the lessons you finish.