Mean by Step-Deviation Method

Definition: The step-deviation method calculates the mean of grouped data by using a change of variable that converts mid-values into small integers called step-deviations (uᵢ).

Key terms:

• xᵢ = class mark (mid-value) of the i-th class = (upper limit + lower limit) / 2
• a = assumed mean (typically the class mark of the middle or highest-frequency class)
• h = class width (difference between upper and lower limits of a class)
• uᵢ = step-deviation = (xᵢ − a) / h
• fᵢ = frequency of the i-th class

Why use step-deviation?

• Direct method requires computing Σfᵢxᵢ with large numbers.
• Assumed mean method requires computing Σfᵢdᵢ where dᵢ can still be large.
• Step-deviation method makes uᵢ small integers (…, −2, −1, 0, 1, 2, …), so Σfᵢuᵢ is easy to compute.

Derivation from the direct method:

1. Direct method: ̄x = Σfᵢxᵢ / Σfᵢ
2. Let a be the assumed mean. Define dᵢ = xᵢ − a, so xᵢ = a + dᵢ.
3. Then: Σfᵢxᵢ = Σfᵢ(a + dᵢ) = aΣfᵢ + Σfᵢdᵢ
4. So: ̄x = a + Σfᵢdᵢ / Σfᵢ (this is the assumed mean method).
5. Now define uᵢ = dᵢ / h = (xᵢ − a) / h, so dᵢ = h × uᵢ.
6. Then: Σfᵢdᵢ = h × Σfᵢuᵢ
7. Substituting: ̄x = a + h(Σfᵢuᵢ / Σfᵢ)

The step-deviation method is algebraically equivalent to both the direct method and the assumed mean method. All three give the same answer. The step-deviation method simply makes the arithmetic easier.

When to use each method:

• Direct method: Use when class marks are small (single or double digits) and frequencies are small. No assumed mean needed.
• Assumed mean method: Use when class marks are large but class widths are unequal.
• Step-deviation method: Use when class marks are large AND class widths are equal. This is the most efficient choice for CBSE problems.

Choosing the assumed mean (a):

• Pick the class mark of the class with the highest frequency (modal class).
• Or pick the class mark nearest to the middle of the distribution.
• The answer is the same regardless of which a you choose — but a good choice makes uᵢ values symmetric around 0, simplifying computation.

Steps to calculate mean by step-deviation method:

1. Find class marks (xᵢ): xᵢ = (lower limit + upper limit) / 2 for each class.
2. Choose assumed mean (a): Pick the xᵢ of the class with highest frequency or the middle class.
3. Find class width (h): h = upper limit − lower limit of any class (must be uniform).
4. Calculate uᵢ: uᵢ = (xᵢ − a) / h for each class. These should be integers.
5. Calculate fᵢuᵢ: Multiply frequency by step-deviation for each class.
6. Find Σfᵢuᵢ: Sum all fᵢuᵢ values (include sign).
7. Find Σfᵢ: Sum all frequencies = N.
8. Apply formula: ̄x = a + h × (Σfᵢuᵢ / Σfᵢ).

Common mistakes:

• Forgetting the sign of uᵢ (negative for classes below a, positive for classes above a).
• Using unequal class widths — step-deviation requires equal class widths.
• Choosing a value that is NOT a class mark — this makes uᵢ non-integer and defeats the purpose.
• Forgetting to multiply Σfᵢuᵢ / Σfᵢ by h in the final step.

Government Census Data:

• Population age groups, income brackets, and household sizes are summarised as grouped data. Step-deviation method efficiently computes mean values for policy planning.

Education:

• Computing average marks of students across classes, schools, or districts from grouped frequency distributions.

Industry:

• Quality control departments calculate average weight, length, or lifespan of products from grouped inspection data.

Economics:

• Calculating average income, expenditure, or savings from income-group data published by statistical agencies.