Lesson 8 of 8 · 22 min
Quantiles and modelling with the normal distribution
Use the inverse normal to find quantiles and cut-off values, find an unknown mean or standard deviation from given probabilities, and solve multi-step modelling problems with normal distributions.
What you will be able to do
- Use the inverse normal to find such that or is a given value.
- Find an unknown or , or both, from given probabilities using -scores.
- Combine normal probabilities with conditional probability and binomial models.
- Evaluate whether a normal model and its answers are reasonable in context.
So far you have started with a value and found a probability. Real questions often run the other way. A mango farm in Bowen sells its heaviest 10% as premium fruit: how heavy must a mango be to make the cut? A machine must underfill no more than 1% of bottles: what mean should it be set to? These are inverse problems: the probability is known and a value or parameter is not.
Definition
Quantiles and the inverse normal
The quantile of is the value with . The 0.9 quantile is the 90th percentile; the 0.5 quantile is the median.
The calculator's inverse normal function takes the left-tail area , the mean and the standard deviation , and returns . For a right-tail condition, convert first: means .
The premium cut-off has 90% of the area to its left and 10% to its right.
Worked example
Grading mangoes with the inverse normal
The masses of mangoes from a Bowen farm are normally distributed with mean 450 g and standard deviation 40 g. The heaviest 10% are sold as premium and the lightest 5% are sent for juice.
(a) Find the minimum mass of a premium mango.
(b) Find the maximum mass of a mango sent for juice.
Give answers correct to 2 decimal places.
Step 1: Define the variable
Let g be the mass of a mango, .
Step 2: Turn the top 10% into a left-tail area
Premium mangoes have with , so .
The inverse normal works with the area to the left of .
Step 3: Use the inverse normal for (a)
Inverse normal with area 0.9, , : g.
Step 4: The lightest 5% for (b)
. Inverse normal with area 0.05: g.
Step 5: Check
and : the premium cut is above the mean and the juice cut further below it, because 5% is a smaller tail than 10%.
Try it yourself first, then check the working one step at a time.
Answer
(a) g (b) g
Method
Write the condition as .
Inverse normal with , and .
Check the side of the mean and the size of .
Watch out for
Entering 0.1 for the top 10%, which gives the bottom 10% cut-off, 398.74 g.
Scores on an aptitude test are normally distributed with mean 80 and standard deviation 6. A prize goes to the top 5% of scores. Find the minimum score needed, correct to 2 decimal places.
If the mean or standard deviation is the unknown, the inverse normal cannot be used on directly, because you don't know its parameters. Work on the standard normal instead: find the -score with the given tail area from , then set it equal to and solve.
Finding an unknown parameter
Write the probability statement
For example .
Find the matching z-score with the inverse normal on N(0, 1)
gives .
Equate to the standardised value
Solve
One unknown: rearrange. Two unknowns: write a second equation from the second condition and solve simultaneously.
The lengths of steel rods are normally distributed with mean 250 mm. 10% of rods are longer than 260 mm. Find the standard deviation, correct to 2 decimal places.
Worked example
Finding the mean and standard deviation from two percentages
The life of a phone battery on one charge is normally distributed. 15% of batteries last less than 20 hours and 10% last more than 32 hours. Find the mean and standard deviation of battery life, correct to 2 decimal places.
Step 1: Write the two conditions
Let . Then and , so .
Step 2: Find the z-scores from N(0, 1)
gives ; gives .
The parameters of are unknown, so use the standard normal, whose parameters are known.
Step 3: Form two equations
Step 4: Solve simultaneously
Subtract: , so . Then .
Step 5: Check
With technology, and for . The mean sits between 20 and 32, nearer 20 because the lower tail (15%) is bigger than the upper tail (10%).
Try it yourself first, then check the working one step at a time.
Answer
hours, hours
Method
Turn each condition into and find .
Write for each.
Solve simultaneously, then check.
Watch out for
Using for the lower value: a value below the mean has a negative -score.
Rounding to 2 decimal places, which shifts the answers in the second decimal place.
Some inverse problems need no technology at all, because symmetry does the work. If and , then 30 is 10 below the mean, and by symmetry too, even though you never find .
and . Without technology, find .
Modelling problems often chain ideas together. A normal model gives the probability that one item has a property; if items are independent, the number of such items in a sample of is then . And "given that" still means conditional probability: , where for nested events like inside the intersection is just the smaller event.
Worked example
Underfilled bottles at a bottling plant
A machine fills bottles labelled 750 mL. The volume mL in a bottle is normally distributed with mean 752 mL and standard deviation 4 mL. Bottles are sold in packs of 6, and fills are independent.
(a) Find the probability that a bottle is underfilled (contains less than 750 mL), correct to 4 decimal places.
(b) Find the probability that a pack contains at least 2 underfilled bottles, correct to 3 decimal places.
(c) Given that a bottle is underfilled, find the probability that it contains less than 745 mL, correct to 4 decimal places.
(d) The company wants only 1% of bottles underfilled, without changing . Find the mean the machine should be set to, correct to 2 decimal places, and comment on the result.
Step 1: Normal probability for (a)
. (normal cdf from to 750, , ).
Step 2: Recognise a binomial count for (b)
Let be the number of underfilled bottles in a pack. Six independent bottles, each underfilled with probability , so .
Fixed number of trials, two outcomes per bottle, the same for each, and independent fills: all four binomial conditions hold.
Step 3: Use the complement
Step 4: Conditional probability for (c)
Every bottle under 745 mL is also under 750 mL, so the intersection is just :
Step 5: Find the z-score for 1% for (d)
needs with , so .
Step 6: Solve for the mean
, so mL.
Step 7: Comment
The machine must overfill by about 9.3 mL on average, which costs the company drink in every bottle. Reducing the spread (servicing the machine) would let them meet the 1% target with a mean closer to 750 mL.
Try it yourself first, then check the working one step at a time.
Answer
(a) (b) (c) (d) mL
Method
Normal model for one item; binomial for a count of independent items.
; for nested events the intersection is the smaller event.
For an unknown mean, find from and solve .
Watch out for
Rounding to 0.31 before the binomial step, which gives 0.601 instead of 0.598.
Writing : the condition changes the denominator.
Common mistake
Rounding too early
Keep the unrounded -score or probability in your calculator memory for the next step. Rounding to 2 decimal places, or a probability to 2 decimal places before it goes into a binomial calculation, can change the final answer in the last place, and markers check it.
Exam tip
Evaluate the model
Questions often end with "comment on the reasonableness" or "evaluate the model". Useful points: does the context suit a symmetric bell-shaped model? Is negligible for a quantity that can't be negative (it should be more than about below the mean)? Are the items independent for a binomial step? Does the answer make sense in size and direction?
Summary
The inverse normal turns a left-tail area into a value: . Convert right tails first.
For an unknown or , find from and solve ; two unknowns need two equations.
Symmetry can answer some inverse questions without technology.
A normal probability per item feeds a binomial model for counts of independent items.
Keep full accuracy between steps, and evaluate the model in context.
Finished the lesson?
Try the 3 quick checks above and the lesson completes itself, or mark it complete now.