4.14 Linear combinations of random variables and unbiased estimates
Studying this course? Keep your progress in one place.
Key facts
- and .
- For independent variables, variances add, even for : .
- (two independent copies) has variance , but has variance .
- The sample mean is an unbiased estimate of .
- The unbiased estimate of is .
One variable, linear transformation
The mean is shifted and scaled like each value; the variance is only scaled, by .
If is a random variable and , are constants then .
For the variance, : adding does not change the spread and multiplying by multiplies the variance by .
(You will not be asked to recall the variance formula for a single variable, but it explains the results for combinations.)
- Expected value
- Variance
Worked example
and income . Find .
- 1
Use with and .
- 2
.
. What is ?
Linear combinations
Means always combine linearly; variances combine with squared coefficients when the variables are independent.
For any random variables, , whether or not they are independent.
If the variables are independent, .
So for independent and : and, because , . Variances add even when the variables are subtracted.
- Mean
- Variance (independent)
Worked example
, , , , with and independent. Find and .
- 1
.
- 2
because variances add.
- 3
.
and are independent with and . Find .
Sum of copies versus doubling
Two independent copies partly cancel each other's extremes, but doubling one variable doubles every extreme.
If and are two independent copies of (for example two separate drivers) then and .
For one variable doubled, but .
The means agree but the variances differ: in a high value of one can be offset by a low value of the other. Check whether the question describes separate independent items or one item counted several times.
| X1 + X2 | 2X | |
|---|---|---|
| Meaning | Two independent copies | One variable doubled |
| Mean | 2E(X) | 2E(X) |
| Variance | 2Var(X) | 4Var(X) |
X1 + X2
- Meaning:
- Two independent copies
- Mean:
- 2E(X)
- Variance:
- 2Var(X)
2X
- Meaning:
- One variable doubled
- Mean:
- 2E(X)
- Variance:
- 4Var(X)
. Find for three independent copies, and .
Unbiased estimate of the mean
An estimate is unbiased if its expected value equals the parameter: on average it is neither too high nor too low.
A sample is used to estimate the properties of a population. The sample mean is an unbiased estimate of the population mean:
so . (The proof is not examined.)
- Sample mean
- Unbiased
Worked example
Masses of six eggs: g. Find an unbiased estimate of .
- 1
Sum .
- 2
.
What does "unbiased" mean for an estimate?
Unbiased estimate of the variance
Divide by , not , to get an unbiased estimate of the population variance.
The sample variance dividing by ,
systematically underestimates . The unbiased estimate of variance divides by :
On most GDCs, is and is (check your model). Square it to get the variance.
- Unbiased variance
Worked example
For the six eggs . Find the unbiased estimate of .
- 1
Use with .
- 2
.
and . Find .
Using estimates in a model
Treat and as and , and say they are estimates.
Once and are found, use them as and in the linear combination formulas.
State clearly that these are estimates. Keep unrounded values until the final answer and give significant figures (money to decimal places).
- 1
Estimate
find the sample mean and s(n-1) squared
- 2
Substitute
use them as mu and sigma squared
- 3
Combine
apply the E and Var rules
- 4
Round last
3 s.f., money 2 d.p.
Worked example
Parcels per driver: and . Payment is AED. Find , and and for two independent drivers.
- 1
AED.
- 2
.
- 3
.
When using and in a combination formula, what do they stand for?
Try an exam question
and are independent random variables with , , and . Let . Find and .
[4 marks]
- [1].
- [1].
- [1] (variances add, independent).
- [1].
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