- Foundation
- About 20 min
- 5 practice questions
Forming classes: size, number, limits and the inclusive and exclusive methods
Answer the five questions in preparing a frequency distribution, use the inclusive and exclusive methods, and adjust class limits to restore continuity.
If something looks wrong, please tell us.
By the end of this lesson you can
- Decide between equal and unequal class intervals and find the number and size of classes.
- Use the exclusive and inclusive methods of forming classes.
- Adjust inclusive class limits to make a continuous distribution and find adjusted class marks.
Building a frequency distribution means answering five questions: (1) equal or unequal class intervals? (2) how many classes? (3) what size of class? (4) how to fix the class limits? (5) how to find the frequency of each class? This lesson answers the first four; the next lesson answers the fifth.
Equal or unequal class intervals?
Equal intervals are used in most cases. Unequal intervals are used in two situations: (i) when the range is very large, as with income, which can run from nearly zero to hundreds of crores of rupees: moderate equal classes would be far too many, while large equal classes would hide information about very low or very high incomes; and (ii) when a large number of values are concentrated in a small part of the range, so that equal classes would lose information about them.
How many classes, and what size?
The number of classes is usually between six and fifteen. The range is the difference between the largest and the smallest values. With equal classes, the two decisions are linked:
Number of classes = range ÷ size of class interval. Range = largest value − smallest value. Decide one and the other follows.
Worked example 1: deciding number and size of classes
Illustrative: monthly food spending of made-up households varies from ₹1,250 to ₹4,730. Step 1, range: 4,730 − 1,250 = ₹3,480. Step 2, try a class size of ₹500: 3,480 ÷ 500 = 6.96, so 7 classes are needed (round up so that every value is covered). Step 3, choose convenient limits: start at ₹1,000: 1,000-1,500, 1,500-2,000, ..., 4,500-5,000. That is (5,000 − 1,000) ÷ 500 = 8 classes, because starting at a round number below 1,250 adds space. Both 7 and 8 lie in the usual range of six to fifteen. Alternative: a class size of ₹1,000 would give only about 3.5, so 4 classes, too few to show the pattern.
How should class limits be fixed?
- Class limits should be definite and clearly stated; open-ended classes such as 'less than 10' or '70 and over' are generally not desirable.
- Limits should be chosen so that observations in each class tend to concentrate around the middle of the class, so that the class mark represents them well.
Exclusive and inclusive methods
Two ways of forming class intervals
-
Exclusive method
- Classes like 0-10, 10-20, 20-30
- Upper limit of one class = lower limit of the next
- A value equal to a limit is excluded from one of the two classes
- Decide in advance: usually 'upper limit excluded', so 10 goes in 10-20
-
Inclusive method
- Classes like 0-10, 11-20, 21-30
- Both limits belong to the class
- Leaves a gap between classes (10 and 11)
- Suits discrete data such as whole-number marks
For discrete variables, both methods can be used. For continuous variables, classes are understood as 'from the lower limit up to, but not including, the upper limit', for example '30 kg and above but under 40 kg', which can be written 30-39.999... kg.
Worked example 2: placing boundary values
Exclusive classes 0-10, 10-20, 20-30, 30-40 with upper limit excluded. Place the values 10, 19, 20 and 30. Working: 10 is excluded from 0-10 (it is that class's upper limit), so it goes in 10-20. 19 lies inside 10-20. 20 is excluded from 10-20 and goes in 20-30. 30 goes in 30-40. Answer: 10-20 gets 10 and 19; 20-30 gets 20; 30-40 gets 30. With the other rule, lower limit excluded, 10 would go in 0-10, 20 in 10-20 and 30 in 20-30; the rule must be fixed in advance and applied consistently.
Adjustment in class interval
With the inclusive method, a continuous variable loses its continuity: between classes 800-899 and 900-999 there is a gap of 1. We restore continuity in four steps:
Making inclusive classes continuous
- Find the gap Lower limit of the second class minus upper limit of the first
- Halve it Gap ÷ 2
- Lower limits Subtract half the gap from every lower limit
- Upper limits Add half the gap to every upper limit
Worked example 3: adjusting class limits
Illustrative: daily earnings (₹) of 60 made-up rickshaw pullers in inclusive classes 300-349 (8), 350-399 (15), 400-449 (22), 450-499 (11), 500-549 (4). Step 1: gap = 350 − 349 = 1. Step 2: half the gap = 0.5. Steps 3 and 4: subtract 0.5 from each lower limit and add 0.5 to each upper limit.
| Original class (₹) | Adjusted class (₹) | Frequency | Adjusted class mark (₹) |
|---|---|---|---|
| 300-349 | 299.5-349.5 | 8 | 324.5 |
| 350-399 | 349.5-399.5 | 15 | 374.5 |
| 400-449 | 399.5-449.5 | 22 | 424.5 |
| 450-499 | 449.5-499.5 | 11 | 474.5 |
| 500-549 | 499.5-549.5 | 4 | 524.5 |
| Total | 60 |
Adjusted class mark = (adjusted upper limit + adjusted lower limit) ÷ 2. For the first class: (349.5 + 299.5) ÷ 2 = 649 ÷ 2 = 324.5. Notice that (349 + 300) ÷ 2 = 324.5 too: the adjustment changes the limits, not the class marks. Now the classes run on without gaps. Check: 8 + 15 + 22 + 11 + 4 = 60.
Key takeaways: use equal class intervals unless the range is huge or values crowd into a small part of it. Usually six to fifteen classes; number of classes = range ÷ class size. Limits should be definite, with observations concentrated near each class mark. The exclusive method needs a rule for boundary values; the inclusive method includes both limits, and for continuous data its gaps are removed by subtracting and adding half the gap.
Check your understanding
-
1. Illustrative: the smallest value in a data set is 18 and the largest is 93. With a class interval of 10, about how many classes are needed?
- 7
- 10
- 9
- 8
Show answer
Answer: D. Range = 93 − 18 = 75. Number of classes = 75 ÷ 10 = 7.5, rounded up to 8 so that every value is covered.
-
2. In the exclusive method with the upper limit excluded, the value 40 is placed in the class:
- 30-40
- 40-50
- both 30-40 and 40-50
- neither class
Show answer
Answer: B. Under 'upper limit excluded', 40 cannot go in 30-40 (where it is the upper limit), so it goes in 40-50, where it is the lower limit.
-
3. Illustrative: inclusive classes are 10-19, 20-29, 30-39. After adjustment for continuity, the class 20-29 becomes:
- 19.5-29.5
- 20-30
- 19-30
- 20.5-29.5
Show answer
Answer: A. Gap = 20 − 19 = 1; half the gap = 0.5. Lower limit 20 − 0.5 = 19.5; upper limit 29 + 0.5 = 29.5. The adjusted class is 19.5-29.5.
-
4. Unequal class intervals are preferred when:
- all values are evenly spread
- the data are qualitative
- the range is very large, as with income
- the variable is discrete
Show answer
Answer: C. The chapter gives two cases for unequal classes: a very large range (such as incomes) and values concentrated in a small part of the range.
-
5. Assertion (A): Open-ended classes such as 'less than 10' are generally not desirable. Reason (R): Class limits should be definite and clearly stated.
- 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: an open-ended class has no definite lower or upper limit, which breaks the rule that limits should be definite (and makes its class mark undefined).
Sign in to keep track of the lessons you finish.