Scribe logoScribeNotes & practice
Sign inStart free
  1. Notes
  2. ›IB Mathematics: Applications and Interpretation
  3. ›4 Statistics and probability
  4. ›4.8 Binomial distribution

IB Mathematics: Applications and Interpretation · Topic 4 · Statistics and probability

4.8 Binomial distribution

Identify situations modelled by a binomial distribution, calculate its probabilities, find its mean and variance, and interpret results in context.

  • 5 min read
  • 6 parts
  • 10 questions
  • Draft
Start a Quick 5 on this topic→Jump to the 10 questions
1/6A binomial model counts successes in repeated trials
  1. 1A binomial model counts successes in repeated trials
  2. 2The probability formula multiplies a count by a probability
  3. 3Technology gives binomial probabilities quickly and accurately
  4. 4The mean and variance depend only on n and p
  5. 5Cumulative probabilities add several outcomes together
  6. 6A probability only means something in its context
  7. Check your recall
  8. Practice: 10 questions
1

Part 1 of 6: A binomial model counts successes in repeated trials

A basketball player takes 10 free throws. Each throw is either a success or a failure, and we count the successes. When a situation like this meets four conditions, a binomial distribution describes the count.

  • There is a fixed number of trials, nnn.
  • Each trial has two outcomes: success or failure.
  • The probability of success, ppp, is the same for every trial.
  • The trials are independent of each other.

We write X∼B(n,p)X\sim \mathrm{B}(n,p)X∼B(n,p), where XXX is the number of successes. The possible values of XXX are 0,1,2,…,n0,1,2,\dots,n0,1,2,…,n.

Common mistake

Picking people from a small group without replacement changes the probability each time. The trials are then not independent, so the model does not fit well.

Key terms · tap one for its definition

binomial distribution

A binomial distribution is the distribution of the number of successes in nnn independent trials, each with the same success probability ppp.

trial

A trial is one repetition of an experiment that ends in exactly one of two outcomes, success or failure.

Part 1 done

2

Part 2 of 6: The probability formula multiplies a count by a probability

Suppose we want exactly rrr successes in nnn trials. One particular order of successes and failures has probability pr(1−p)n−rp^r(1-p)^{n-r}pr(1−p)n−r. We then need the number of different orders.

The binomial coefficient (nr)\binom{n}{r}(rn​) gives that number of orders. Multiplying the two parts gives the formula for P(X=r)P(X=r)P(X=r).

P(X=r)=(nr) pr(1−p)n−rP(X=r)=\binom{n}{r}\,p^{r}(1-p)^{n-r}P(X=r)=(rn​)pr(1−p)n−r

Here (nr)=n!r! (n−r)!\binom{n}{r}=\frac{n!}{r!\,(n-r)!}(rn​)=r!(n−r)!n!​. All the probabilities for r=0r=0r=0 to r=nr=nr=n add up to 1.

Take n=4n=4n=4 and r=1r=1r=1. The single success can come first, second, third or fourth. That gives (41)=4\binom{4}{1}=4(14​)=4 orders. Each order has the same probability, so we multiply by 4.

Key term

binomial coefficient

The binomial coefficient (nr)\binom{n}{r}(rn​) is the number of ways to choose rrr successes from nnn trials.

Part 2 done

Quick check

One question on the part you just read

Easy

Identify the situation that is best modelled by a binomial distribution.
Show answer and explanation

Answer: A · Worked explanation

Twelve tosses give a fixed number of independent trials, each with two outcomes and a constant probability. The number of tosses needed for a first head is not a count out of a fixed number of trials. Waiting time and height are measurements, not counts of successes.
3

Part 3 of 6: Technology gives binomial probabilities quickly and accurately

Now apply the formula to a real case. On a calculator, use the binomial probability function for one value of rrr. Enter nnn, ppp and rrr in that order.

The same method works for any nnn and ppp. Check that ppp is the probability of the outcome you are counting. State the model first, so a reader can follow your working.

Worked example

Customers who buy

Each customer entering a shop buys something with probability 0.3, independently of others. Eight customers enter. Let XXX be the number who buy. Find P(X=3)P(X=3)P(X=3).
  1. 1
    The model is X∼B(8,0.3)X\sim \mathrm{B}(8,0.3)X∼B(8,0.3).
  2. 2
    Use P(X=r)=(nr)pr(1−p)n−rP(X=r)=\binom{n}{r}p^r(1-p)^{n-r}P(X=r)=(rn​)pr(1−p)n−r.
  3. 3
    Substitute: P(X=3)=(83)(0.3)3(0.7)5P(X=3)=\binom{8}{3}(0.3)^3(0.7)^5P(X=3)=(38​)(0.3)3(0.7)5.
  4. 4
    Evaluate: 56×0.027×0.16807≈0.25456\times 0.027\times 0.16807\approx 0.25456×0.027×0.16807≈0.254.

Answer: P(X=3)≈0.254P(X=3)\approx 0.254P(X=3)≈0.254.

Figure 1. Each point shows the probability of that number of buyers when X∼B(8,0.3)X\sim \mathrm{B}(8,0.3)X∼B(8,0.3). The most likely value is 2.

The graph shows how the probabilities spread over the possible values. The highest point is at r=2r=2r=2. Probabilities beyond r=6r=6r=6 are too small to see.

Exam tip

Write the model, such as X∼B(8,0.3)X\sim \mathrm{B}(8,0.3)X∼B(8,0.3), before any calculation. Quote answers to three significant figures unless told otherwise.

Part 3 done

4

Part 4 of 6: The mean and variance depend only on n and p

Over many repetitions of the same experiment, the counts settle around an average. The expected value E(X)E(X)E(X) is the long-run average, and for a binomial distribution it equals npnpnp.

The variance Var(X)\mathrm{Var}(X)Var(X) measures how widely the counts spread around that average. For a binomial distribution, Var(X)=np(1−p)\mathrm{Var}(X)=np(1-p)Var(X)=np(1−p). The standard deviation is the square root of the variance.

The variance is largest when p=0.5p=0.5p=0.5, where success and failure are equally likely. It is small when ppp is near 0 or 1, because the result is then easy to predict. The mean need not be a whole number, even though XXX always is.

Worked example

Germinating seeds

A seed germinates with probability 0.25. Forty seeds are sown independently. Find the mean, variance and standard deviation of the number that germinate.
  1. 1
    The model is X∼B(40,0.25)X\sim \mathrm{B}(40,0.25)X∼B(40,0.25).
  2. 2
    Mean: E(X)=np=40×0.25=10E(X)=np=40\times 0.25=10E(X)=np=40×0.25=10.
  3. 3
    Variance: np(1−p)=40×0.25×0.75=7.5np(1-p)=40\times 0.25\times 0.75=7.5np(1−p)=40×0.25×0.75=7.5.
  4. 4
    Standard deviation: 7.5≈2.74\sqrt{7.5}\approx 2.747.5​≈2.74.

Answer: The mean is 10 seeds, the variance is 7.5 and the standard deviation is about 2.74 seeds.

Key terms · tap one for its definition

expected value

The expected value E(X)E(X)E(X) of a random variable XXX is its long-run average over many repetitions.

variance

The variance Var(X)\mathrm{Var}(X)Var(X) of a random variable XXX is the mean of the squared distances of its values from the mean.

Part 4 done

Quick check

One question on the part you just read

Easy

State the mean of X∼B(20,0.35)X\sim \mathrm{B}(20,0.35)X∼B(20,0.35).
Show answer and explanation

Answer: A · Worked explanation

The mean is np=20×0.35=7np=20\times 0.35=7np=20×0.35=7. The value 4.55 is the variance np(1−p)np(1-p)np(1−p), not the mean. The value 13 is n(1−p)n(1-p)n(1−p), the expected number of failures.
5

Part 5 of 6: Cumulative probabilities add several outcomes together

Often a question asks about a range of values, such as at least three buyers. A cumulative probability P(X≤r)P(X\le r)P(X≤r) is the probability of rrr successes or fewer. Calculators give it directly.

Use the fact that all probabilities total 1. So P(X≥3)=1−P(X≤2)P(X\ge 3)=1-P(X\le 2)P(X≥3)=1−P(X≤2). Convert the wording into an inequality before calculating.

Turning wording into a calculation

WordingInequalityCalculation
fewer than 3X≤2X\le 2X≤2P(X≤2)P(X\le 2)P(X≤2)
at most 3X≤3X\le 3X≤3P(X≤3)P(X\le 3)P(X≤3)
more than 3X≥4X\ge 4X≥41−P(X≤3)1-P(X\le 3)1−P(X≤3)
at least 3X≥3X\ge 3X≥31−P(X≤2)1-P(X\le 2)1−P(X≤2)
Wording
fewer than 3
Inequality
X≤2X\le 2X≤2
Calculation
P(X≤2)P(X\le 2)P(X≤2)
Wording
at most 3
Inequality
X≤3X\le 3X≤3
Calculation
P(X≤3)P(X\le 3)P(X≤3)
Wording
more than 3
Inequality
X≥4X\ge 4X≥4
Calculation
1−P(X≤3)1-P(X\le 3)1−P(X≤3)
Wording
at least 3
Inequality
X≥3X\ge 3X≥3
Calculation
1−P(X≤2)1-P(X\le 2)1−P(X≤2)

Calculators usually give P(X≤r)P(X\le r)P(X≤r). For P(a≤X≤b)P(a\le X\le b)P(a≤X≤b), use P(X≤b)−P(X≤a−1)P(X\le b)-P(X\le a-1)P(X≤b)−P(X≤a−1). Take care with the lower end.

Common mistake

For P(X≥3)P(X\ge 3)P(X≥3), subtracting P(X≤3)P(X\le 3)P(X≤3) is wrong. That removes the case X=3X=3X=3, which should stay in.

Key term

cumulative probability

A cumulative probability P(X≤r)P(X\le r)P(X≤r) is the probability that the random variable takes the value rrr or any smaller value.

Part 5 done

6

Part 6 of 6: A probability only means something in its context

For the eight customers, P(X≥3)≈0.448P(X\ge 3)\approx 0.448P(X≥3)≈0.448. In context, this means that about 45% of groups of eight such customers would include at least three buyers.

The mean is np=8×0.3=2.4np=8\times 0.3=2.4np=8×0.3=2.4. We do not expect exactly 2.4 buyers in any one group. It is the average over many groups.

Unlikely results can challenge the model. If seven of the eight customers bought, P(X≥7)≈0.0013P(X\ge 7)\approx 0.0013P(X≥7)≈0.0013. That is rare when p=0.3p=0.3p=0.3, so the true probability may be higher.

Always answer in a full sentence that names the situation. Quote the probability as a percentage when that reads more naturally.

Note read

Check your recall[15 marks]

6 written questions. Answer each one in your head or on paper, then open the mark scheme.

  1. 1.State[3 marks]

    State three conditions that must hold for a random variable to follow a binomial distribution.

    Show mark schemeHide mark scheme

    Model answer

    There is a fixed number of trials. Each trial has two outcomes, with the same probability of success every time. The trials are independent.

    • 1 mark for stating that the number of trials is fixed
    • 1 mark for stating that each trial has two outcomes with a constant probability of success
    • 1 mark for stating that the trials are independent
  2. 2.Calculate[3 marks]

    Calculate P(X=2)P(X=2)P(X=2) when X∼B(5,0.4)X\sim \mathrm{B}(5,0.4)X∼B(5,0.4).

    Show mark schemeHide mark scheme

    Model answer

    P(X=2)=(52)(0.4)2(0.6)3=10×0.16×0.216=0.3456≈0.346P(X=2)=\binom{5}{2}(0.4)^2(0.6)^3=10\times 0.16\times 0.216=0.3456\approx 0.346P(X=2)=(25​)(0.4)2(0.6)3=10×0.16×0.216=0.3456≈0.346.

    • 1 mark for using (52)=10\binom{5}{2}=10(25​)=10
    • 1 mark for substituting (0.4)2(0.6)3(0.4)^2(0.6)^3(0.4)2(0.6)3
    • 1 mark for obtaining 0.346
  3. 3.Determine[2 marks]

    Determine the mean and variance of X∼B(50,0.2)X\sim \mathrm{B}(50,0.2)X∼B(50,0.2).

    Show mark schemeHide mark scheme

    Model answer

    Mean =np=50×0.2=10=np=50\times 0.2=10=np=50×0.2=10. Variance =np(1−p)=50×0.2×0.8=8=np(1-p)=50\times 0.2\times 0.8=8=np(1−p)=50×0.2×0.8=8.

    • 1 mark for finding the mean as 10
    • 1 mark for finding the variance as 8
  4. 4.Explain[2 marks]

    Explain why P(X≥3)P(X\ge 3)P(X≥3) can be found as 1−P(X≤2)1-P(X\le 2)1−P(X≤2).

    Show mark schemeHide mark scheme

    Model answer

    All the probabilities of the possible values total 1. The values not included in X≥3X\ge 3X≥3 are 0, 1 and 2, so subtracting P(X≤2)P(X\le 2)P(X≤2) leaves P(X≥3)P(X\ge 3)P(X≥3).

    • 1 mark for stating that the probabilities of all outcomes total 1
    • 1 mark for identifying that X≤2X\le 2X≤2 is the complement of X≥3X\ge 3X≥3
  5. 5.Explain[3 marks]

    Explain why the number of aces in five cards dealt without replacement from a small pack is not well modelled by a binomial distribution.

    Show mark schemeHide mark scheme

    Model answer

    Each card removed changes the make-up of the pack. The probability of an ace therefore changes from card to card. The trials are not independent, and the success probability is not constant.

    • 1 mark for stating that removing cards changes the pack
    • 1 mark for stating that the probability of success is not constant
    • 1 mark for stating that the trials are not independent
  6. 6.Calculate[2 marks]

    Calculate P(X≥1)P(X\ge 1)P(X≥1) when X∼B(5,0.4)X\sim \mathrm{B}(5,0.4)X∼B(5,0.4).

    Show mark schemeHide mark scheme

    Model answer

    P(X≥1)=1−P(X=0)=1−0.65=1−0.07776=0.92224≈0.922P(X\ge 1)=1-P(X=0)=1-0.6^5=1-0.07776=0.92224\approx 0.922P(X≥1)=1−P(X=0)=1−0.65=1−0.07776=0.92224≈0.922.

    • 1 mark for using 1−P(X=0)1-P(X=0)1−P(X=0) with 0.650.6^50.65
    • 1 mark for obtaining 0.922

Practice this topic

10 quick-fire multiple-choice questions, easy to hard. Tap an answer to see if you're right and the worked explanation. (The written questions with mark schemes are under “Check your recall” above.)

0 right0 of 10 answered

Includes the 2 quick checks in the note above.

3.

Easy[1 mark]

In the model X∼B(n,p)X\sim \mathrm{B}(n,p)X∼B(n,p), what does nnn represent?
Show answer and explanation

Answer: A · Worked explanation

The letter nnn is the fixed number of trials. The probability of success is ppp, and the number of successes observed is the random variable XXX. The variance is np(1−p)np(1-p)np(1−p), which uses nnn but is not equal to it.
4.

Medium·Calculate[1 mark]

Calculate P(X=2)P(X=2)P(X=2) when X∼B(6,0.5)X\sim \mathrm{B}(6,0.5)X∼B(6,0.5).
Show answer and explanation

Answer: A · Worked explanation

P(X=2)=(62)(0.5)6=15×0.015625=0.234P(X=2)=\binom{6}{2}(0.5)^6=15\times 0.015625=0.234P(X=2)=(26​)(0.5)6=15×0.015625=0.234. The value 0.0156 leaves out the binomial coefficient. The value 0.469 is the total for two and four successes together.
5.

Medium·Calculate[1 mark]

Calculate P(X≥1)P(X\ge 1)P(X≥1) when X∼B(10,0.2)X\sim \mathrm{B}(10,0.2)X∼B(10,0.2).
Show answer and explanation

Answer: A · Worked explanation

Use P(X≥1)=1−P(X=0)=1−0.810≈1−0.107=0.893P(X\ge 1)=1-P(X=0)=1-0.8^{10}\approx 1-0.107=0.893P(X≥1)=1−P(X=0)=1−0.810≈1−0.107=0.893. The value 0.107 is P(X=0)P(X=0)P(X=0) itself, which answers the opposite question. The value 0.376 is P(X≤1)P(X\le 1)P(X≤1), which adds in one success.
6.

Medium·Determine[2 marks]

A binomial random variable has mean 20 and variance 12. Determine the number of trials, nnn.
Show answer and explanation

Answer: A · Worked explanation

From np=20np=20np=20 and np(1−p)=12np(1-p)=12np(1−p)=12, we get 1−p=0.61-p=0.61−p=0.6, so p=0.4p=0.4p=0.4. Then n=200.4=50n=\frac{20}{0.4}=50n=0.420​=50. The value 32 comes from adding the mean and variance, and 8 from subtracting them.
7.

Medium·Identify[2 marks]

A machine makes items that are defective with probability 0.05. For samples of 30 items, E(X)=1.5E(X)=1.5E(X)=1.5 defective items. Identify the correct interpretation.
Show answer and explanation

Answer: A · Worked explanation

The expected value is a long-run average, so over many samples the mean count is 1.5. A count cannot equal 1.5 in one sample, so it cannot be the most likely value. The defect rate is 5%, not 1.5%.
8.

Hard·Calculate[2 marks]

Calculate P(X≥3)P(X\ge 3)P(X≥3) when X∼B(8,0.3)X\sim \mathrm{B}(8,0.3)X∼B(8,0.3).
Show answer and explanation

Answer: A · Worked explanation

Use P(X≥3)=1−P(X≤2)=1−0.552=0.448P(X\ge 3)=1-P(X\le 2)=1-0.552=0.448P(X≥3)=1−P(X≤2)=1−0.552=0.448. The value 0.552 is P(X≤2)P(X\le 2)P(X≤2) itself. The value 0.194 is P(X≥4)P(X\ge 4)P(X≥4), which wrongly leaves out the case X=3X=3X=3.
9.

Hard·Calculate[2 marks]

A student guesses all 20 questions on a test. Each question has four options, so X∼B(20,0.25)X\sim \mathrm{B}(20,0.25)X∼B(20,0.25). Calculate P(X≥8)P(X\ge 8)P(X≥8).
Show answer and explanation

Answer: A · Worked explanation

Use P(X≥8)=1−P(X≤7)=1−0.898=0.102P(X\ge 8)=1-P(X\le 7)=1-0.898=0.102P(X≥8)=1−P(X≤7)=1−0.898=0.102. The value 0.898 is P(X≤7)P(X\le 7)P(X≤7). The value 0.061 is only P(X=8)P(X=8)P(X=8), and 0.041 is P(X≥9)P(X\ge 9)P(X≥9) because it drops the case X=8X=8X=8.
10.

Hard·Determine[2 marks]

Each trial succeeds with probability 0.1. Determine the smallest number of trials nnn for which P(X≥1)>0.99P(X\ge 1)>0.99P(X≥1)>0.99.
Show answer and explanation

Answer: A · Worked explanation

We need 1−0.9n>0.991-0.9^n>0.991−0.9n>0.99, so 0.9n<0.010.9^n<0.010.9n<0.01. Since 0.943≈0.01080.9^{43}\approx 0.01080.943≈0.0108 is too large and 0.944≈0.00970.9^{44}\approx 0.00970.944≈0.0097 works, n=44n=44n=44. Rounding down to 43 gives only about 0.989, which is below 0.99.

Keep going

Next topic4.9 Normal distributionPrevious topic4.7 Discrete random variables

More in Topic 4 · Statistics and probability

  1. 4.4Correlation and regressionNotes · 10 questions
  2. 4.5Probability conceptsNotes · 10 questions
  3. 4.6Combined events and diagramsNotes · 10 questions
  4. 4.7Discrete random variablesNotes · 10 questions
  5. 4.8Binomial distributionNotes · 10 questions
  6. 4.9Normal distributionNotes · 10 questions
  7. 4.10Spearman's rank correlationNotes · 10 questions
  8. 4.11Chi-squared and t-testsNotes · 10 questions
  9. 4.12Designing data collectionNotes · 10 questions· HL only

All IB Mathematics: Applications and Interpretation topics →

Draft: written by Scribe and checked automatically, not yet by a subject reviewer.

Practice questions are original, written by Scribe and checked automatically for correctness.

Topic codes follow the official numbering. Not endorsed by IB Diploma Programme or any exam board.

On this page

0/6 read

  1. 1A binomial model counts successes in repeated trials
  2. 2The probability formula multiplies a count by a probability
  3. 3Technology gives binomial probabilities quickly and accurately
  4. 4The mean and variance depend only on n and p
  5. 5Cumulative probabilities add several outcomes together
  6. 6A probability only means something in its context
  7. Check your recall
  8. Practice: 10 questions
All coursesScribeHow it worksPricingPrivacyTerms

Notes and questions are written by Scribe in our own words. Topic codes follow the official course numbering so you can find your place. Not produced or endorsed by the IB, College Board, AQA, OCR, Pearson Edexcel or any exam board.

© 2026 Scribe

Probabilities for eight customers

Probability P(X = r)0246800.10.20.3Number of successes r
  • P(X = r)