IP AMaths Notes (Upper Sec, Year 3-4): 20) Statistics - Standard Deviation

Study guideUpdated 14 Oct 2026
Marcus Pang
Reviewed by
Marcus Pang·Managing Director (Maths)

Compute mean, variance, and standard deviation for raw and grouped data in IP AMaths.

For Integrated Programme students: Your current school materials, teacher instructions, and assessment scope take precedence because IP topic sequence and depth vary by school. This is an Eclat IP guide, not the O-Level / SEC G3 exam-track guide.

How this chapter applies

  • Eclat core: standard-deviation calculation and comparison are retained as an Eclat IP bridge where the school includes statistics in upper-secondary Mathematics.
  • School-sensitive extension: the whole chapter is outside K341 core, although its content overlaps K310 Topic S1 and may support later statistics pathways.
  • 2027 national comparison: K341 has no statistics topic; K310 Topic S1 includes standard deviation for grouped and ungrouped data and comparison using mean and standard deviation.
  • Check your school: check whether the chapter belongs to E-Math, an IP extension, or later pathway preparation in the current school.
  • Exam-track route: use the separate O-Level and SEC G3 Additional Mathematics notes for K341 topic ownership.
Q: What does IP AMaths Notes (Upper Sec, Year 3-4): 20) Statistics - Standard Deviation cover?
A: Compute mean, variance, and standard deviation for raw and grouped data in IP AMaths.

Standard deviation quantifies spread. Handle both raw datasets and grouped frequencies.

Keep the full topic roadmap handy via our IP Maths tuition hub so you can jump into related drills, quizzes, or diagnostics as you move through these notes.

New to the Integrated Programme? Start with What is IP? | Browse all free IP notes.

The core idea is simple: Standard deviation measures how spread out a dataset is.

Use it as a working check: Find the mean first, measure each value's distance from the mean, square those distances, average them, then take the square root.

Then go one layer deeper: Example: for grouped data, replace each class interval with its midpoint before multiplying by frequency. The midpoint is an estimate, so state grouped-data answers to a sensible accuracy.

1 Formulae

Use the population convention throughout this chapter, with at least one observation or positive total frequency. Grouped-data formulae use class midpoints and estimate the original mean, variance, and standard deviation; they are exact only for the midpoint-represented data.

  • Mean: xˉ=∑xn \bar{x} = \dfrac{\sum x}{n} .
  • Variance (population): σ2=∑(x−xˉ)2n \sigma^2 = \dfrac{\sum (x - \bar{x})^2}{n} .
  • For grouped data with midpoints mi m_i and frequencies fi f_i :
    • xˉ=∑fimi∑fi \bar{x} = \dfrac{\sum f_i m_i}{\sum f_i} .
    • σ2=∑fi(mi−xˉ)2∑fi \sigma^2 = \dfrac{\sum f_i (m_i - \bar{x})^2}{\sum f_i} .

Working-table checkpoint

Before calculating standard deviation, build the table that matches the data format. This prevents you from using the raw-value formula on a frequency table or treating a class interval as one exact value.

Data formatColumns to createMean usesVariance uses
Raw listxx, (x−xˉ)2(x-\bar{x})^2∑x÷n\sum x \div n∑(x−xˉ)2÷n\sum (x-\bar{x})^2 \div n
Frequency tablexx, ff, fxfx, f(x−xˉ)2f(x-\bar{x})^2∑fx÷∑f\sum fx \div \sum f∑f(x−xˉ)2÷∑f\sum f(x-\bar{x})^2 \div \sum f
Grouped dataclass interval, midpoint mm, ff, fmfm, f(m−xˉ)2f(m-\bar{x})^2∑fm÷∑f\sum fm \div \sum f∑f(m−xˉ)2÷∑f\sum f(m-\bar{x})^2 \div \sum f
Calculator shortcutxx, ff, x2x^2, fx2fx^2 or m2m^2, fm2fm^2Same mean column as above∑fx2∑f−xˉ2\frac{\sum fx^2}{\sum f}-\bar{x}^2, using mm for grouped data

Worked check: if the table says value 66 occurs 44 times, its contribution to the mean numerator is 4×6=244 \times 6 = 24, not just 66. After finding the mean, its contribution to the variance numerator is 4(6−xˉ)24(6-\bar{x})^2.

Misconception check: frequency is a multiplier. It tells you how many times a value or midpoint is counted, so it must appear in both the mean numerator and the variance numerator.

2 Spread interpretation checkpoint

Before calculating, identify whether the question changes every value in the same way or changes the spread itself. This helps you avoid recomputing when the spread can be reasoned out.

Data changeWhat happens to the mean?What happens to standard deviation?Why
Add kk to every value.Increases by kk.Unchanged.Every value and the mean move together, so distances from the mean stay the same.
Subtract kk from every value.Decreases by kk.Unchanged.The whole dataset shifts left by the same amount.
Multiply every value by kk.Multiplies by kk.Multiplies by ∣k∣\lvert k\rvert.Distances from the mean are stretched by the scale factor.
Replace grouped data by midpoints.Becomes an estimate.Becomes an estimate.Each class is represented by its midpoint, not by the exact original values.

Common trap: standard deviation measures spread around the mean, not the size of the mean itself. Adding the same constant to every value changes the mean but not the spread.

Coded-data reversal checkpoint

If a question defines a coded variable, undo the coding in the right order. Division by the coding scale requires a non-zero scale. Translation changes the mean only; scaling changes both the mean and the standard deviation.

Coding statementMean relationshipStandard deviation relationshipCommon trap
y=x−ay = x - axˉ=yˉ+a\bar{x} = \bar{y} + aσx=σy\sigma_x = \sigma_yAdding aa to the standard deviation as well.
y=x−aby = \dfrac{x - a}{b}xˉ=a+byˉ\bar{x} = a + b\bar{y}σx=∣b∣σy\sigma_x = \lvert b\rvert\sigma_yForgetting to multiply the spread by the scale factor.
y=bx+ay = bx + ayˉ=bxˉ+a\bar{y} = b\bar{x} + aσy=∣b∣σx\sigma_y = \lvert b\rvert\sigma_xUsing the mean formula for standard deviation.

Worked check: if y=x−5010y = \dfrac{x - 50}{10}, yˉ=1.8\bar{y} = 1.8, and σy=0.6\sigma_y = 0.6, then

xˉ=50+10(1.8)=68,σx=10(0.6)=6. \bar{x} = 50 + 10(1.8) = 68, \qquad \sigma_x = 10(0.6) = 6.

Misconception check: the standard deviation ignores the +50+50 shift because all values and the mean move together. It responds only to the stretch factor 1010.

3 Worked example - Raw data

Scores: 4,6,8,10,12 4, 6, 8, 10, 12 .

  1. Mean: xˉ=4+6+8+10+125=8 \bar{x} = \dfrac{4 + 6 + 8 + 10 + 12}{5} = 8 .
  2. Compute squared deviations: (4−8)2=16 (4 - 8)^2 = 16 , (6−8)2=4 (6 - 8)^2 = 4 , (8−8)2=0 (8 - 8)^2 = 0 , (10−8)2=4 (10 - 8)^2 = 4 , (12−8)2=16 (12 - 8)^2 = 16 .
  3. Variance: σ2=16+4+0+4+165=8 \sigma^2 = \dfrac{16 + 4 + 0 + 4 + 16}{5} = 8 .
  4. Standard deviation: σ=8=22 \sigma = \sqrt{8} = 2\sqrt{2} .

4 Worked example - Grouped data

Class intervals 0≤x<5 0 \leq x \lt 5 , 5≤x<10 5 \leq x \lt 10 , 10≤x<15 10 \leq x \lt 15 with frequencies 3,5,2 3, 5, 2 respectively.

  1. Midpoints: m1=2.5 m_1 = 2.5 , m2=7.5 m_2 = 7.5 , m3=12.5 m_3 = 12.5 .
  2. Mean: xˉ=3(2.5)+5(7.5)+2(12.5)3+5+2=7.5+37.5+2510=7.0 \bar{x} = \dfrac{3(2.5) + 5(7.5) + 2(12.5)}{3 + 5 + 2} = \dfrac{7.5 + 37.5 + 25}{10} = 7.0 .
  3. Variance numerator: 3(2.5−7)2+5(7.5−7)2+2(12.5−7)2=3(20.25)+5(0.25)+2(30.25)=60.75+1.25+60.5=122.5 3(2.5 - 7)^2 + 5(7.5 - 7)^2 + 2(12.5 - 7)^2 = 3(20.25) + 5(0.25) + 2(30.25) = 60.75 + 1.25 + 60.5 = 122.5 .
  4. Variance: σ2=122.510=12.25 \sigma^2 = \dfrac{122.5}{10} = 12.25 .
  5. Standard deviation: σ=12.25=3.5 \sigma = \sqrt{12.25} = 3.5 .

5 Worked example - Frequency table with repeated values

A dataset records test attempts with the following frequencies: value 2 2 occurs four times, 5 5 occurs three times, and 9 9 occurs three times. Compute the mean and standard deviation.

  1. Total frequency n=4+3+3=10 n = 4 + 3 + 3 = 10 .
  2. Mean: xˉ=4(2)+3(5)+3(9)10=8+15+2710=5 \bar{x} = \dfrac{4(2) + 3(5) + 3(9)}{10} = \dfrac{8 + 15 + 27}{10} = 5 .
  3. Squared deviations:
    • For x=2 x = 2 : (2−5)2=9 (2 - 5)^2 = 9 ; contribution 4×9=36 4 \times 9 = 36 .
    • For x=5 x = 5 : (5−5)2=0 (5 - 5)^2 = 0 ; contribution 3×0=0 3 \times 0 = 0 .
    • For x=9 x = 9 : (9−5)2=16 (9 - 5)^2 = 16 ; contribution 3×16=48 3 \times 16 = 48 .
  4. Variance: σ2=36+0+4810=8410=8.4 \sigma^2 = \dfrac{36 + 0 + 48}{10} = \dfrac{84}{10} = 8.4 .
  5. Standard deviation: σ=8.4≈2.90 \sigma = \sqrt{8.4} \approx 2.90 (3 s.f.).

Answer: mean 5 5 , standard deviation ≈2.90 \approx 2.90 .

6 Practice Quiz

Review how shifts and scaling affect spread, and rehearse grouped-data calculations so you can respond quickly to statistics prompts.

7 Try this

Given four consecutive class intervals starting at zero, with class boundaries 0, 4, 8, 12, and 16, class width 4 4 and frequencies 2,7,9,4 2, 7, 9, 4 , construct the midpoints, compute xˉ \bar{x} , and evaluate σ \sigma accurately.


Sources

  1. National comparator - SEAB - 2027 SEC G3 Additional Mathematics K341 syllabus
  2. MOE - Integrated Programme