Lesson 6 of 7 · 16 min
Margin of error, confidence and sample size
See how the margin of error depends on the sample size and the confidence level, and choose the smallest sample that delivers a required margin of error.
What you will be able to do
- Explain how the margin of error changes with the sample size and the confidence level.
- Predict the new margin of error when is multiplied by a factor.
- Find the minimum sample size for a required margin of error, with a prior estimate of or using .
A polling company wants its next poll to be accurate to within 2 percentage points. How many people does it need to ring? Before answering, see how the margin of error behaves.
The horizontal axis is the sample size . Increase (more confidence): the whole curve rises. Move away from 0.5: the curve falls.
Key idea
What controls the margin of error
- Sample size: is proportional to . Multiplying by divides by , so four times the sample halves the margin.
- Confidence level: a higher level needs a bigger , so a wider interval. Precision and confidence pull against each other for a fixed .
- The proportion: is largest at , so estimates near 50% have the biggest margins.
| 100 | 400 | 1000 | 1600 | 2500 | |
|---|---|---|---|---|---|
| 0.098 | 0.049 | 0.031 | 0.0245 | 0.0196 |
A survey has a margin of error of 0.06. A second survey uses the same confidence level and gets the same , but has nine times the sample size. What is its margin of error?
Worked example
How big a sample halves the margin?
A survey of 500 people gave a 95% confidence interval for with a margin of error of 0.040. Assuming stays about the same, what sample size would give a margin of error of 0.020?
Step 1: Write the margin in terms of n
, so is proportional to .
Step 2: Compare the margins
The new margin is half the old one, so must double.
If , then halving means multiplying by 2.
Step 3: Find the new n
Doubling multiplies by : .
Try it yourself first, then check the working one step at a time.
Answer
About 2000 people: four times the original sample.
Method
.
Dividing by needs times the sample size.
Watch out for
Doubling the sample to 1000, which only divides the margin by , to about 0.028.
Now turn the question round. You want to be at most some value. Solve for :
Tip
Which p̂ to use before you have data
You need before you have collected the sample. Use an estimate from a pilot study or a previous survey if you have one. If you have none, use : it makes , its largest possible value, so the you get is enough whatever the true proportion is.
Why 0.5 gives the largest sample size
has at , and , so the maximum is . Any other gives a smaller and so a smaller required .
Worked example
Choose a sample size for a required margin of error
A researcher wants to estimate the proportion of Queensland adults who have had skin cancer removed, to within 0.03 with 95% confidence.
(a) A pilot study suggests the proportion is about 0.2. Find the minimum sample size.
(b) Find the minimum sample size if there is no pilot estimate.
Step 1: Set up the inequality
Step 2: Substitute the pilot estimate
Step 3: Round up
The smallest whole number at least 682.95 is 683.
With 682 people the margin of error would be slightly more than 0.03.
Step 4: Use p̂ = 0.5 with no estimate
, so .
is largest at 0.5, so this works whatever the true proportion is.
Try it yourself first, then check the working one step at a time.
Answer
(a) 683 (b) 1068
Method
.
Use a pilot if there is one; otherwise .
Round up.
Watch out for
Rounding 682.95 to 682, or 1067.11 to 1067.
Using the width (0.06) instead of the margin (0.03).
Find the smallest sample size that gives a margin of error of at most 0.05 for a 95% confidence interval when nothing is known about . Use .
Common mistake
Rounding the sample size
Always round a minimum sample size up, even 864.36 → 865: rounding down gives a margin of error slightly bigger than required. And check whether the question gives the width of the interval: a width of 0.04 means .
Summary
is proportional to : multiplying by divides by ; four times the sample halves the margin.
For fixed , higher confidence means bigger and a wider interval.
The minimum sample size is , rounded up.
With no prior estimate use , which gives the largest (safest) .
Finished the lesson?
Try the 2 quick checks above and the lesson completes itself, or mark it complete now.