4.8 · SLPaper 1Paper 2

Binomial distribution

In a minute

A counts how many times something happens in a fixed number of independent tries, each with the same chance. You write X∼B(n,p)X \sim \mathrm{B}(n, p), find its probabilities on your GDC, and use npnp for the number you expect.

You'll be able to

  • Decide whether a binomial distribution fits a situation, write it as X∼B(n,p)X \sim \mathrm{B}(n, p), and state its assumptions in context.
  • Find P(X=r)\mathrm{P}(X = r) with your GDC, and see where it comes from in a small case.
  • Turn "at most", "at least", "fewer than", "more than" and "between" into the right GDC calculation.
  • Find and interpret the mean and of X∼B(n,p)X \sim \mathrm{B}(n, p).
  • Use npnp as an , including for batches that meet a condition.
Before you start3 quick questions on what this builds on
Check yourself
The probability that a parcel is delivered late is 0.060.06. A courier delivers 350350 parcels. Find the expected number delivered late.
Check yourself
Events AA and BB are independent, with P(A)=0.3\mathrm{P}(A) = 0.3 and P(B)=0.8\mathrm{P}(B) = 0.8. Find P(A∩B)\mathrm{P}(A \cap B).
Check yourself
A YY takes the values 11, 22 and 44 with probabilities 0.250.25, 0.450.45 and 0.30.3. Find E(Y)\mathrm{E}(Y).

Revise first: 4.3 Central tendency and dispersion, 4.5 Probability foundations and expected value, 4.6 Probability diagrams, rules and independence and 4.7 Discrete random variables and expected value

When is a situation binomial?

How many of 2525 batteries are faulty? How many of 3030 patients recover? Each question counts successes in a fixed number of tries. When every try behaves the same way, a binomial distribution gives the probability of each count.

"Success" is only a label for the outcome you count: it can be a faulty battery. Independent means one trial's result doesn't change the chances for any other, as in 4.6.

In real situations these conditions are assumptions of the model. Questions often ask you to state one, or to judge whether it is reasonable.

Worked exampleA factory makes thousands of phone batteries a day, and 3%3\% of them are faulty. An inspector picks 2525 batteries at random from one day's output. Let XX be the number of faulty batteries. (a) Write down the distribution of XX. (b) State two assumptions you have made, and comment on whether each is reasonable.

Try it first, then reveal one step at a time.

  1. Each battery picked is a trial: faulty (the success you count) or not. There are n=25n = 25 trials.
Worked exampleIs a binomial model suitable for XX? If not, say which condition fails. (a) A darts player throws until she hits the bullseye; XX is the number of throws. (b) XX is the number of rainy days in the next 1010 days. (c) A teacher picks 44 students, one at a time, from a class of 1515 boys and 1010 girls; XX is the number of girls picked.

Try it first, then reveal one step at a time.

  1. (a) She stops when she succeeds, so the number of throws is not fixed.
Check yourself
A gym finds that 70%70\% of new members still attend after three months. For a group of 1818 new members, it models XX, the number still attending, as X∼B(18,0.7)X \sim \mathrm{B}(18, 0.7). Which is an assumption of this model?
Check yourself
Which of these random variables has a binomial distribution?

The probability of exactly r successes

Before you hand the work to your GDC, see where a binomial probability comes from. A small case is enough.

Worked exampleOn her ride to school, Mei passes 33 sets of traffic lights. Each is red when she arrives with probability 0.40.4, independently of the others. Find the probability that exactly 22 of the lights are red.

Try it first, then reveal one step at a time.

  1. Let XX be the number of red lights, so X∼B(3,0.4)X \sim \mathrm{B}(3, 0.4). Write R for red and G for not red, with P(G)=1−0.4=0.6\mathrm{P}(\text{G}) = 1 - 0.4 = 0.6.
Tree diagram for three traffic lights, each red (R) with probability 0.4 or not red (G) with probability 0.6. The eight paths and their probabilities are RRR 0.064, RRG 0.096, RGR 0.096, RGG 0.144, GRR 0.096, GRG 0.144, GGR 0.144 and GGG 0.216. The three paths with exactly two reds, RRG, RGR and GRR, are highlighted, each with probability 0.096. R G R G R G R G R G R G R G 0.4 0.6 0.4 0.6 0.4 0.6 0.4 0.6 0.4 0.6 0.4 0.6 0.4 0.6 RRR: 0.4 × 0.4 × 0.4 = 0.064 RRG: 0.4 × 0.4 × 0.6 = 0.096 RGR: 0.4 × 0.6 × 0.4 = 0.096 RGG: 0.4 × 0.6 × 0.6 = 0.144 GRR: 0.6 × 0.4 × 0.4 = 0.096 GRG: 0.6 × 0.4 × 0.6 = 0.144 GGR: 0.6 × 0.6 × 0.4 = 0.144 GGG: 0.6 × 0.6 × 0.6 = 0.216
Three of the eight paths have exactly two reds, and each has probability 0.0960.096.

Two counts need only one path: P(X=0)=(1−p)n\mathrm{P}(X = 0) = (1-p)^{n}, as every trial fails, and P(X=n)=pn\mathrm{P}(X = n) = p^{n}.

With more trials the number of orders grows fast: 99 successes in 2020 trials can happen in 167 960167\,960 orders. Your GDC's binomial pdf counts them and adds them up for you.

Worked exampleIn a large city, 35%35\% of adults cycle to work at least once a week. A random sample of 2020 adults from the city is taken. Use your calculator to find the probability that exactly 99 of them cycle to work at least once a week. Give your answer to 3 s.f.

Try it first, then reveal one step at a time.

  1. Let XX be the number in the sample who cycle. There are n=20n = 20 trials, each a yes or no.
Check yourself
Ravi wins each game of an online puzzle with probability 0.850.85, independently of other games. He plays 44 games, and XX is the number he wins. Find the probability that he wins all 44.
Check yourself
In a large city, 14%14\% of cars are electric. A random sample of 3232 cars is taken. Find the probability that exactly 66 of them are electric. Give your answer to 3 s.f.

At most, at least and between

Most questions ask about a range of counts, such as "at most 33". Your GDC's binomial cdf adds P(X=0)\mathrm{P}(X = 0) up to P(X=k)\mathrm{P}(X = k), giving P(X≤k)\mathrm{P}(X \le k) in one step.

Everything else comes from P(X≤k)\mathrm{P}(X \le k) and the . XX only takes whole numbers, so "fewer than 55" means X≤4X \le 4, and "more than 55" means X≥6X \ge 6.

Learn this
at most kP(X≤k)fewer than kP(X≤k−1)at least kP(X≥k)=1−P(X≤k−1)more than kP(X>k)=1−P(X≤k)a to b inclusiveP(a≤X≤b)=P(X≤b)−P(X≤a−1)\begin{array}{ll} \text{at most } k & \mathrm{P}(X \le k) \\ \text{fewer than } k & \mathrm{P}(X \le k - 1) \\ \text{at least } k & \mathrm{P}(X \ge k) = 1 - \mathrm{P}(X \le k - 1) \\ \text{more than } k & \mathrm{P}(X > k) = 1 - \mathrm{P}(X \le k) \\ a \text{ to } b \text{ inclusive} & \mathrm{P}(a \le X \le b) = \mathrm{P}(X \le b) - \mathrm{P}(X \le a - 1) \end{array}

In the chart below, "at least 88" shades the bars from 88 up. Its complement is the bars 00 to 77, so you subtract P(X≤7)\mathrm{P}(X \le 7).

Binomial probabilitiesDrag the slider
0.000.050.100.150.200.2502468101214161820X ~ B(20, 0.3)shaded: P(X ≥ 8)
20
0.30

8

Probability = 0.2277 (P(X ≥ 8))

Mean np = 6.00, variance np(1 − p) = 4.20

Each bar is P(X = k) = C(n, k) pᵏ (1 − p)ⁿ⁻ᵏ. The shaded bars make up the event, and adding their heights gives its probability.
Worked exampleAn airline sells 160160 tickets for a flight with 154154 seats. Each ticket holder turns up with probability 0.920.92. (a) Find the probability that more passengers turn up than there are seats. Give your answer to 3 s.f. (b) Interpret your answer, and comment on one assumption of your model.

Try it first, then reveal one step at a time.

  1. Let XX be the number of ticket holders who turn up. Assume each turns up with probability 0.920.92, independently of the others. Then X∼B(160,0.92)X \sim \mathrm{B}(160, 0.92).
Worked exampleA library finds that 22%22\% of borrowed books are returned late. On one day, 4545 books are borrowed. Assume each book is returned late with probability 0.220.22, independently of the others. Find the probability that between 99 and 1313 of these books, inclusive, are returned late. Give your answer to 3 s.f.

Try it first, then reveal one step at a time.

  1. Let XX be the number returned late, so X∼B(45,0.22)X \sim \mathrm{B}(45, 0.22).
Check yourself
X∼B(25,0.3)X \sim \mathrm{B}(25, 0.3). Find P(X<5)\mathrm{P}(X < 5).
Check yourself
A clinic finds that 8%8\% of booked appointments are missed. On one day, 4040 appointments are booked. Assuming appointments are missed independently, find the probability that at least 55 are missed. Give your answer to 3 s.f.

Mean, variance and expected number

In 4.5 you found an as n×P(A)n \times \mathrm{P}(A). A binomial count is the same idea. With nn trials and success probability pp, you expect npnp successes.

In the formula booklet
E(X)=np\mathrm{E}(X) = np

E(X)\mathrm{E}(X) is the mean of XX: the average number of successes if you repeated all nn trials many times. It need not be a whole number.

The measures how widely the count spreads around its mean. Its square root is the .

In the formula booklet
Var(X)=np(1−p)\mathrm{Var}(X) = np(1-p)

Both formulas are in the formula booklet; you don't need to prove them. Since 1−p<11 - p < 1, the variance is smaller than the mean whenever p>0p > 0: a quick check.

Worked exampleAt a call centre, 15%15\% of calls are complaints. In one shift the centre takes 240240 calls. Let XX be the number of complaints, and assume X∼B(240,0.15)X \sim \mathrm{B}(240, 0.15). (a) Find the mean and the variance of XX. (b) Interpret the mean in context.

Try it first, then reveal one step at a time.

  1. (a) Here n=240n = 240 and p=0.15p = 0.15, so 1−p=0.851 - p = 0.85.
Worked exampleA bakery bakes croissants in trays of 1616. Each croissant comes out perfect with probability 0.930.93, independently of the others. A tray sells at full price if at least 1414 of its croissants are perfect. (a) Find the probability that a tray sells at full price. (b) The bakery bakes 4040 trays in a week. Find the expected number of trays that sell at full price. Give your answers to 3 s.f.

Try it first, then reveal one step at a time.

  1. (a) Let XX be the number of perfect croissants on a tray: X∼B(16,0.93)X \sim \mathrm{B}(16, 0.93).
Check yourself
X∼B(60,0.35)X \sim \mathrm{B}(60, 0.35). Find Var(X)\mathrm{Var}(X).
Check yourself
A courier models the number of late parcels in a van of 5050 as X∼B(50,0.25)X \sim \mathrm{B}(50, 0.25), so E(X)=12.5\mathrm{E}(X) = 12.5. Which statement is correct?
Check yourself
A charity texts 850850 supporters. Each replies with probability 0.060.06, independently of the others. Find the probability that more supporters reply than the expected number. Give your answer to 3 s.f.

Common mistakes

  • Writing P(X≥k)=1−P(X≤k)\mathrm{P}(X \ge k) = 1 - \mathrm{P}(X \le k). That throws away X=kX = k as well. Use 1−P(X≤k−1)1 - \mathrm{P}(X \le k - 1).
  • Reading "fewer than 55" as X≤5X \le 5, or "more than 55" as X≥5X \ge 5. For a whole-number count they are X≤4X \le 4 and X≥6X \ge 6.
  • Using a binomial model when picking without replacement from a small group. The probability changes after each pick.
  • Rounding a GDC value before subtracting or multiplying with it. Carry the full value and round only the final answer.

Exam tips

  • Find a binomial probability: write X∼B(n,p)X \sim \mathrm{B}(n, p) and the probability statement, such as P(X≥6)=1−P(X≤5)\mathrm{P}(X \ge 6) = 1 - \mathrm{P}(X \le 5), before the GDC value.
  • State an assumption: name independence or the constant probability, in context.
  • Give a probability exactly or to 3 s.f.; when you round, keep trailing zeros: 0.2500.250 for 0.24996…0.24996\ldots, not 0.250.25; 0.009860.00986, not 0.010.01.
  • Find an expected number: write npnp, or nn times a probability, with the numbers in, then the value. Don't round it to a whole number.

Key takeaways

Learn thisX∼B(n,p)X \sim \mathrm{B}(n, p) counts the successes in a fixed number nn of independent trials, each with two outcomes and the same probability pp of success.
Learn thisOn a GDC, binomial pdf gives P(X=r)\mathrm{P}(X = r) and binomial cdf gives P(X≤k)\mathrm{P}(X \le k).
Learn thisFor binomial XX (whole numbers only): P(X≥k)=1−P(X≤k−1)\mathrm{P}(X \ge k) = 1 - \mathrm{P}(X \le k - 1) and P(X>k)=1−P(X≤k)\mathrm{P}(X > k) = 1 - \mathrm{P}(X \le k).
In bookletE(X)=np\mathrm{E}(X) = np
In bookletVar(X)=np(1−p)\mathrm{Var}(X) = np(1-p)
Learn thisFor X∼B(n,p)X \sim \mathrm{B}(n, p), npnp is the expected number of successes: a long-run average that need not be a whole number. The standard deviation is np(1−p)\sqrt{np(1-p)}.

Practise this

26 past-paper questions on Binomial distribution in the AI HL bank, each with a mark scheme and a worked explanation.

Practise Binomial distribution →