Estimators, bias and the sampling distribution of the mean
Studying this course? Keep your progress in one place.
Key facts
- Bias is ; unbiased means .
- An estimator is a statistic used to estimate a parameter; an estimate is its value for one sample.
- Unbiased estimates: and .
- and ; the standard error is .
Estimators and estimates
An estimator is a random variable used to estimate a parameter; an estimate is a number.
A parameter is a fixed but usually unknown number describing a population, such as or . A statistic is a quantity calculated from a random sample that involves no unknown parameter, such as .
An estimator is a statistic used to estimate a parameter; an estimate is the number it takes for one sample. is an estimator of , and is an estimate.
- 1
Population
Parameter μ: fixed, usually unknown
- 2
Random sample
X₁, …, Xₙ
- 3
Estimator X̄
A statistic: a random variable
- 4
Estimate x̄ = 12.5
The number for one sample
Parameter
- A fixed number for the population
- Usually unknown: μ, σ²
Statistic
- Calculated from a sample
- A random variable: X̄
Estimator
- A statistic used to estimate
- Capital letter: X̄
Estimate
- Its value for one sample
- Lower case: x̄ = 12.5
A sample gives . Is an estimator or an estimate of ?
Bias
An estimator is unbiased if its expected value equals the parameter.
For an estimator of a parameter , the bias is . If , then is an unbiased estimator: on average, over many samples, it gives the true value.
To test a linear estimator use .
- Bias
- Unbiased
Worked example
are independent with mean . Show that is unbiased, and find the bias of .
- 1
, so is unbiased.
- 2
.
- 3
Bias .
for an estimator of . What is the bias?
Unbiased estimates
Use for the mean and divide by for the variance.
From a random sample , is an unbiased estimate of and the sample variance is an unbiased estimate of .
Dividing by is biased: its expected value is , which underestimates . No proofs are required.
- Unbiased estimate of μ
- Unbiased estimate of σ²
Worked example
A sample has , and . Find unbiased estimates of the mean and variance.
- 1
.
- 2
.
- 3
, so .
A sample has and . What is the unbiased estimate of the variance?
Distribution of the sample mean
is centred on with variance , so it is narrower than one observation.
If is a random sample from a population with mean and variance , then and . The standard deviation is the standard error.
If the population is Normal, then exactly . This is the sampling distribution of the mean. When is unknown the standard error is estimated by .
and . What is the standard error of ?
Using the sample mean
State and standardise with the standard error.
Standardise with . Because the standard error is , it halves when the sample size is multiplied by , so larger samples give more reliable estimates.
- Standard error
- n × 4standard error halves
Worked example
Apple masses are and . Find , and compare with for one apple.
- 1
, with standard error .
- 2
.
- 3
Single apple: . Sample mean: .
The sample size is multiplied by . What happens to the standard error?
Try an exam question
A random sample of observations has and . Find unbiased estimates of the population mean and variance.
[4 marks]
- [1].
- [1]Use .
- [1].
- [1].
That's the notes covered.
Carry on to the next subtopic.
Try a question
What is an unbiased estimate of the population mean?
1 mark, marked against the mark scheme
What is an unbiased estimate of the population mean?
1 mark, marked against the mark scheme