Normal distribution
In a minute
Heights, masses and many other measurements are often modelled by the : a symmetric bell-shaped curve centred on the . Its probabilities are areas under the curve. You estimate them with the , find them with your GDC, and run the GDC backwards to find a value from a probability.
You'll be able to
- Describe the normal curve, its properties and where it occurs, read , and sketch it with a region shaded.
- Use the 68–95–99.7 rule to estimate probabilities and expected numbers, and to judge whether a model is sensible.
- Find normal probabilities with your GDC and say what they mean in context.
- Find a value from a probability with , for a lower tail, an upper tail or a middle region.
Before you start3 quick questions on what this builds on
Revise first: 4.2 Data presentation, 4.3 Central tendency and dispersion, 4.5 Probability foundations and expected value and 4.7 Discrete random variables and expected value
The normal curve
Draw a of 2000 adult heights with narrow bars. Most heights sit near the average, and extreme ones are rare on both sides. The outline is a smooth, symmetric bell: the normal curve.
This shape appears when many small, independent effects add up. Heights, masses, machine-made lengths and measurement errors are often close to normal. Incomes and waiting times are usually skewed, so they are not.
A height is a : it can take any value in a range, unlike the separate values in 4.7. Its probabilities are areas under a curve.
The second number in is the variance, not the standard deviation. So has . Questions often write to make easy to see.
1. The curve is symmetric about the vertical line through . So the mean, median and mode all equal .
2. The total area under the curve is , because is certain to take some value.
3. The curve gets closer and closer to the horizontal axis on both sides but never touches it. Values far from are possible, just very unlikely.
4. sets where the centre is. sets the spread: a larger gives a lower, wider curve, because the area must stay .
Symmetry gives some probabilities with no working: half the area lies on each side of , and tails the same distance from have equal areas.
To sketch a normal curve, draw a symmetric bell that flattens towards the axis without touching it. Mark in the centre, label each bound on the correct side of , and shade the region you want.
Try it first, then reveal one step at a time.
- (a) Read the model: the mean is and the variance is . The standard deviation is the square root of the variance: cm.
- (b) is the mean, and the curve is symmetric about it. So half of all hand spans are below cm.
Try it first, then reveal one step at a time.
- The two tails have equal areas, so and are the same distance from the mean.
- The mean is halfway between them: .
- The area to the left of the mean is . Take away the tail below : .
- Sketch check: the strip from to is much bigger than the tail, as says.
The 68–95–99.7 rule
Every normal curve has the same shape: slides it along and stretches it. So the fraction within one standard deviation of the mean is the same for every normal distribution.
This is the , for normal distributions only. Learn it: it is not in the formula booklet. The values are rounded; the GDC gives for one standard deviation.
Use symmetry to split the bands. Half of is , between and . Half of is , so lies between and .
Half of is . So lies above , and the same below .
Try it first, then reveal one step at a time.
- Write each bound as standard deviations from the mean: and .
- The interval is , which holds about of values.
Try it first, then reveal one step at a time.
- Convert the bounds: and .
- From to is half of : .
- From to is half of : . Take it away: .
- The expected number is : .
- Interpret: about of the phones last between and hours.
Normal probabilities on your GDC
The rule only works at whole numbers of standard deviations. For other bounds, use your GDC's normal cdf.
1. Sketch the curve, mark and the bounds, and shade the area you want.
2. Write the probability and the model, such as with .
3. Enter the lower bound, upper bound, and . Enter , not the variance.
4. For less than , use the lower bound (type -1E99). For more than , use the upper bound (1E99).
Try it first, then reveal one step at a time.
- Sketch: in the centre, to its left and to its right. Shade between them.
- Write the calculation: with , .
- Normal cdf with lower bound , upper bound , , gives
- Sense check: the interval is a little wider than , which holds about . So a value a little above makes sense.
Try it first, then reveal one step at a time.
- (a) Sketch: is left of the mean, so expect a small left tail, under .
- (a) Write . Normal cdf with lower bound , upper bound , , gives
- (b) Expected number . Use the stored value:
- (b) Give it to 3 s.f.: . An expected number need not be a whole number.
- Interpret: about of the runners are expected to finish in under minutes.
Try it first, then reveal one step at a time.
- Write . Normal cdf with lower bound , upper bound , , gives
- Interpret: the model says about of customers wait a negative time.
- Comment: a waiting time can't be negative, so the model is not realistic for short waits. A curve this wide, centred this close to , spills below .
Inverse normal: from a probability to a value
Sometimes you know the area and need the boundary: the time the fastest beat, or the length only the longest exceed. This is an calculation.
In inverse normal questions and are always given. You only need the area, and which side of it is on.
1. : enter the area with the tail set to left (the default).
2. : the area to the left of is . Enter , or enter with the tail set to right if your GDC has that option.
3. A middle region of probability , centred on : the two tails share , so each holds . The lower bound has to its left, and the upper bound has .
Try it first, then reveal one step at a time.
- Sketch: the fastest times are a small left tail, so is below .
- Write the condition: . It is already a left-hand area.
- Inverse normal with area , , gives
- Check and interpret: , as the sketch said. An assembler needs under about minutes to win a badge.
Try it first, then reveal one step at a time.
- Write the condition: .
- Turn it into a left-hand area: .
- Inverse normal with area , , gives (Or area with the tail set to right.)
- Check: the longest cucumbers are above the mean, and .
Try it first, then reveal one step at a time.
- Outside the middle lies , shared equally: in each tail.
- Lower bound: , so inverse normal gives
- Upper bound: the area to the left of is , so
- Check the symmetry: and .
- Interpret: of these birds have wingspans between about cm and cm.
Common mistakes
- Typing the variance into the GDC's standard deviation field. In the second number is , so take its square root first.
- Using as a left-hand area when . Enter , or set the tail to right.
- Putting all the leftover area in one tail. For the middle , each tail holds : the bounds have and to their left.
- Rounding an expected number to a whole number, such as for , or using a rounded probability to find it. Use the stored value and give 3 s.f.
- Copying a GDC display such as 6.13E-3 as . A probability can't be more than : write .
- Giving a bare answer to 2 s.f., such as for With no working shown, it loses the accuracy mark and there is no method mark to fall back on. Write the set-up and give 3 s.f.
Exam tips
- Find / calculate: write the probability statement, such as , or the GDC syntax with its four numbers, then the answer to 3 s.f. The written line earns the method mark.
- Sketch: a symmetric bell that flattens towards the axis, the mean in the centre, each bound labelled on the correct side of the mean, and the region shaded.
- Write down: needs no working. Use symmetry and the 68–95–99.7 rule for quick answers and to sense-check GDC results.
- Comment on a model: find the probability of an impossible value, such as a negative time or a mark above the maximum, and say what it means in context.
Key takeaways
Practise this
26 past-paper questions on Normal distribution in the AI HL bank, each with a mark scheme and a worked explanation.