Yates' correction

Yates' correction

Spec SE5 · AQA A-Level Further Maths: Revision notes

Studying this course? Keep your progress in one place.

Key facts

  • The chi-squared statistic approximates discrete frequencies with a continuous distribution, so it tends to be too large when ν\nu is small.
  • Yates' correction applies only to a 2×22\times2 table, where ν=1\nu=1.
  • X2=∑(∣O−E∣−0.5)2EX^2=\sum\dfrac{(|O-E|-0.5)^2}{E}.
  • Compare with the critical value for ν=1\nu=1: 3.8413.841 at 5%5\%, 6.6356.635 at 1%1\%.
  • The corrected statistic is always smaller, so it is more cautious about claiming an association.

Why a correction is needed

Discrete observed frequencies are approximated by a continuous distribution, which overstates the statistic when ν\nu is small.

The chi-squared statistic ∑(O−E)2E\sum\frac{(O-E)^2}{E} is only an approximation: observed frequencies are discrete whereas the chi-squared distribution is continuous.

When the degrees of freedom are small this tends to make the statistic too large, so the test rejects H0H_0 too often.

Yates' correction (a continuity correction) reduces this effect.

Uncorrected

Statistic:
Too large for small ν
Rejects H0:
Too often

With Yates' correction

Statistic:
Smaller
Rejects H0:
Less often

Why does the uncorrected chi-squared statistic tend to be too large for small ν\nu?

When to apply it

Only for a 2×22\times2 table, where ν=1\nu=1.

Apply Yates' correction when the table is a 2×22\times2 contingency table, so that ν=(2−1)(2−1)=1\nu=(2-1)(2-1)=1. For larger tables (ν>1\nu>1) it is not used.

The convention that every expected frequency should be greater than 5 still applies.

2×22\times2

Degrees of freedom:
1
Use Yates' correction?:
Yes

2×32\times3

Degrees of freedom:
2
Use Yates' correction?:
No

3×33\times3

Degrees of freedom:
4
Use Yates' correction?:
No

For which table is Yates' correction used?

How to apply it

Subtract 0.50.5 from each ∣O−E∣|O-E| before squaring and dividing by EE.

X2=∑(∣Oi−Ei∣−0.5)2Ei.X^2=\sum\frac{(|O_i-E_i|-0.5)^2}{E_i}.

Find each expected frequency as usual, take the modulus of O−EO-E, subtract 0.50.5, then square and divide by EE. Compare with the critical value for ν=1\nu=1: 3.8413.841 at 5%5\% and 6.6356.635 at 1%1\%.

In a 2×22\times2 table all four values of ∣O−E∣|O-E| are equal, so work it out once and reuse it.

  1. 1

    Expected frequencies

    row total × column total ÷ grand total

  2. 2

    Find |O − E|

    the modulus, so it is never negative

  3. 3

    Subtract 0.5

    from each |O − E|

  4. 4

    Square and divide by E

    then sum over all four cells

  5. 5

    Compare

    with the critical value for ν = 1

Applying Yates' correction

Worked example

Method X: 17 pass, 8 fail. Method Y: 10 pass, 15 fail. Test at the 5% level whether the pass rate depends on method, using Yates' correction.

In the example, what does the correction change about the conclusion?

Interpreting the result

The corrected statistic is smaller, so state the conclusion in context and note any borderline result.

Yates' correction always gives a smaller statistic than the uncorrected formula, so it is more cautious about claiming an association.

State the conclusion in context, for example "there is insufficient evidence that the pass rate depends on the training method".

If the corrected statistic is close to the critical value, say the result is borderline and that more data would help.

  • Corrected statisticsmaller than uncorrected
  • The 0.5 goesinside the bracket, on each |O − E|

Where is the 0.50.5 subtracted in Yates' correction?

Try an exam question

Method X: 17 of 25 trainees pass and 8 fail. Method Y: 10 of 25 pass and 15 fail. Carry out a chi-squared test with Yates' correction at the 5% level to decide whether pass rate depends on the method. The 5% critical value for ν=1\nu=1 is 3.8413.841.

[5 marks]

That's the notes covered.

Carry on to the next subtopic.

Try a question

Assuming no association, find the expected number of seeds given fertiliser that germinate.

1 mark, marked against the mark scheme

Revision notes