Choosing a distribution and approximations

Choosing a distribution and approximations

Spec 4.3 · Edexcel A-Level Maths: Revision notes

Studying this course? Keep your progress in one place.

Key facts

  • Binomial: a fixed number of trials, two outcomes, independent, constant pp. State the conditions in context.
  • The binomial fails with dependence, a changing probability (sampling without replacement from a small population) or a non-fixed nn.
  • Normal suits a continuous, symmetrical, bell-shaped variable; it is poor for skewed or discrete data.
  • If X∼B(n,p)X\sim B(n,p) with nn large and pp near 0.50.5, use Y∼N(np, np(1−p))Y\sim N\big(np,\,np(1-p)\big).
  • Apply a continuity correction: P(X≤k)≈P(Y<k+0.5)P(X\le k)\approx P(Y<k+0.5).

Choosing the binomial model

When all four conditions hold; state them in context.

X∼B(n,p)X\sim B(n,p) is suitable for a fixed number of trials with two outcomes, independent trials and constant probability pp. Ten seeds each germinating with probability 0.450.45, independently, is binomial.

State the conditions in context, for example ‘each seed germinates independently of the others, with the same probability’.

  1. 1

    Fixed n

    A fixed number of trials.

  2. 2

    Two outcomes

    Success or failure.

  3. 3

    Independent

    One trial does not affect another.

  4. 4

    Constant p

    The same probability each time.

Choosing the binomial model

Ten seeds each germinate independently with probability 0.45. Which model fits the number germinating?

When the binomial may not be appropriate

Name the failing condition: independence, constant pp, a fixed nn, or random selection.

Independence fails for students in one tutor group or family members sharing a habit. The probability changes when sampling without replacement from a small population (drawing 6 cards from 10). The number of trials is not fixed if you count until something happens.

To improve the model, take a random sample from the whole population.

Independence

Fails when:
Trials share a cause
Example:
Same tutor group

Constant p

Fails when:
Probability changes
Example:
Without replacement from 10 cards

Fixed n

Fails when:
Counting until something happens
Example:
Not a set number of trials

Six cards are drawn without replacement from a pack of ten. Why is the number of red cards not binomial?

When the Normal may not be appropriate

When the data are skewed, bounded, discrete with few values, or have more than one peak.

The Normal suits a continuous, symmetrical, bell-shaped variable such as heights or masses. It is a poor model for skewed data such as incomes, a bounded or discrete variable with only a few values, or more than one peak.

A histogram roughly symmetrical about its mean, with most values within about two standard deviations, supports a Normal model.

Suitable

Type:
Continuous
Shape:
Symmetrical, bell-shaped
Example:
e.g. heights, masses

Poor model

Type:
Skewed or bounded
Shape:
Discrete with few values
Example:
e.g. incomes, sixes in 5 rolls

Which variable is least suitable for a Normal model?

Normal approximation to the binomial

For large nn and pp close to 0.50.5, use N(np,np(1−p))N\big(np,np(1-p)\big).

The Normal approximation uses mean npnp and variance np(1−p)np(1-p) (not its square root). For X∼B(60,0.45)X\sim B(60,0.45): Y∼N(27,14.85)Y\sim N(27,14.85).

It works because the binomial is roughly symmetrical when pp is near 0.50.5. It is poor when pp is close to 0 or 1 or npnp is small: for B(50,0.05)B(50,0.05) it gives positive probability to negative values.

  • X∼B(n,p)X\sim B(n,p)Y∼N(np, np(1−p))Y\sim N\big(np,\ np(1-p)\big)

X∼B(100,0.4)X\sim B(100,0.4). Which Normal approximation is correct?

The continuity correction

Treat each integer kk as the interval from k−0.5k-0.5 to k+0.5k+0.5.

A binomial takes integer values but the Normal is continuous, so apply a continuity correction. Write the integers you want first: X≥30X\ge30 means 30, 31, … so the boundary is 29.529.5.

P(X≤k)≈P(Y<k+0.5)P(X\le k)\approx P(Y<k+0.5), P(X≥k)≈P(Y>k−0.5)P(X\ge k)\approx P(Y>k-0.5), P(X<k)≈P(Y<k−0.5)P(X<k)\approx P(Y<k-0.5), P(X>k)≈P(Y>k+0.5)P(X>k)\approx P(Y>k+0.5).

36384042444648505239.548.5

Worked example

X∼B(80,0.55)X\sim B(80,0.55). Estimate P(40≤X≤48)P(40\le X\le48).

Using a Normal approximation, P(X>30)P(X>30) for a binomial XX becomes which probability?

Try an exam question

X∼B(100,0.4)X\sim B(100,0.4). Use a Normal approximation to estimate P(X≤35)P(X\le35).

[4 marks]

That's the notes covered.

Carry on to the next subtopic.

Try a question

Which distribution models XX exactly?

1 mark, marked against the mark scheme

Revision notes