Converting units: E(aX + b) and Var(aX + b)
The midday temperature, degrees Celsius, in a city during July has mean and standard deviation . The temperature in degrees Fahrenheit is , where .
(a) Find the mean and standard deviation of .
(b) It is now given that . Find the probability that on a randomly chosen day in July the midday temperature is more than degrees Fahrenheit.
- 1
(a) Expectation is linear, so both the multiplier and the added constant act on the mean: .
- 2
Adding shifts every value by the same amount, so it does not change the spread. Only the multiplier matters, and it is squared for the variance: .
- 3
Take the square root for the standard deviation (equivalently, ).
- 4
(b) A linear function of a normal variable is normal, so . Standardise, using the standard deviation (not the variance).
- 5
Read from the table and take the upper tail.
Answer
(a) Mean , standard deviation (b)
Examiner tip
The commonest error is : the constant is added to the mean but never to the variance. In (b), dividing by instead of loses the standardising mark; converting back to Celsius () and standardising with gives the same and is equally acceptable.