The binomial distribution
Studying this course? Keep your progress in one place.
Key facts
- needs a fixed , two outcomes, constant and independent trials.
- .
- Tables give : rewrite , and ranges in that form.
- Mean and variance , so the variance is less than the mean.
- Comment on the model by saying which condition may fail, in context.
When binomial applies
When there is a fixed number of independent trials, each with two outcomes and the same probability of success.
A binomial distribution models the number of successes in trials provided:
- there is a fixed number of trials, ;
- each trial has two outcomes, success or failure;
- is the same for every trial;
- the trials are independent.
Write and . The number of sixes in rolls of a fair die is .
The number of hearts in a hand of 5 cards dealt from a pack of 52. Is this binomial?
Calculating probabilities
Multiply the number of arrangements by the probability of one arrangement.
The coefficient counts the arrangements of the successes among the trials. Each arrangement has probability .
- P(X = r)
Worked example
. Find .
- 1
.
- 2
, and .
. Find .
Cumulative probabilities
Tables give , so rewrite every probability in that form.
Tables stop at . For , let . A calculator gives the same values.
For a cumulative probability, "at least" means a complement: .
Worked example
. Find and .
- 1
.
- 2
.
Worked example
. Find .
- 1
Let .
- 2
is the same as , so .
Write in terms of a cumulative probability.
Mean and variance
The mean is and the variance is , so the variance is always less than the mean.
For you can quote the mean and the variance without derivation. The standard deviation is .
For example has mean and variance .
- E(X)
- Var(X)
Worked example
A binomial distribution has mean and variance . Find and .
- 1
Divide: .
- 2
So .
- 3
Then gives .
. Find the mean and variance.
Commenting on the model
Say which condition may fail, in the context.
Say whether each condition is reasonable in the context. For binomial counts the variance is smaller than the mean. If the observed variance is much larger, trials are probably not independent or varies.
Independence
- Trials affect each other, for example sampling without replacement from a small population
Constant
- The probability changes with time, person or batch
Two outcomes
- A trial has several outcomes that need simplifying
Fixed
- The number of trials depends on the outcomes
A coin is tossed until the first head appears and is the number of tosses. Why is not binomial?
Try an exam question
A biased coin has probability of landing heads. It is tossed times and is the number of heads. State the distribution of , find , and find the mean and variance of .
[4 marks]
- [1].
- [1].
- [1].
- [1]Mean and variance .
That's the notes covered.
Carry on to the next subtopic.
Try a question
Find .
1 mark, marked against the mark scheme
Find .
1 mark, marked against the mark scheme