Edexcel International A Level Further Maths
Estimators, bias and the sampling distribution of the mean
Total 27 marks
Name
Class
Date
- 1A random sample of 8 observations of a variable gives and .(a)What is an unbiased estimate of the population mean?[1 mark]
- A
- B
- C
- D
Show the mark scheme
Mark scheme
Answer: D(b)What is an unbiased estimate of the population variance?[1 mark]- A
- B
- C
- D
Show the mark scheme
Mark scheme
Answer: A(c)Calculate an estimate of the standard error of the sample mean.[2 marks]Show the mark scheme
Mark scheme
M1: (using their )
A1: (awrt)
Accept:
Do not accept: (this is the variance of the sample mean)Total for question 1: 4 marks
- 2, and are independent observations from a population with mean and variance .(a)Which of the following is an unbiased estimator of ?[1 mark]
- A
- B
- C
- D
Show the mark scheme
Mark scheme
Answer: B(b)What is the standard error of the sample mean ?[1 mark]- A
- B
- C
- D
Show the mark scheme
Mark scheme
Answer: C(c)Show that is a biased estimator of , and state the bias.[2 marks]Show the mark scheme
Mark scheme
M1:
A1: so is biased, with bias (it overestimates)
Accept: biasTotal for question 2: 4 marks
- 3The masses of apples from an orchard are Normally distributed with mean g and standard deviation g. Random samples of apples are taken, and the sample mean is calculated for each sample.(a)State the distribution of , and find .[3 marks]
Show the mark scheme
Mark scheme
B1: , i.e. variance
M1: standardise,
A1: (awrt, )
Do not accept: standardising with instead of(b)(i) Find the probability that the sample mean of 16 apples is within g of g.[4 marks]
(ii) Find the probability that a single apple has a mass within g of g, and explain what a comparison of the two probabilities shows about the sample mean.Show the mark scheme
Mark scheme
M1: (i) with
A1: (i) (awrt)
B1: (ii) (awrt) for a single apple, using standard deviation
R1: (ii) the sample mean is much more likely to be close to , because its standard error is smaller than (it is less variable)Total for question 3: 7 marks
- 4The times, in seconds, taken by 10 randomly chosen runners to complete a sprint are summarised by and . The times are modelled as a random sample from a population with unknown mean and unknown variance .(a)(i) Calculate unbiased estimates of and .[6 marks]
(ii) Calculate an estimate of the standard error of the sample mean.Show the mark scheme
Mark scheme
M1: (i)
A1: (i)
M1: (i)
A1: (i) (awrt, )
M1: (ii)
A1: (ii) (awrt)
Accept: follow-through from their(b)(i) Calculate the value of for this sample.[6 marks]
(ii) Explain why this is not used as an estimator of .
(iii) Assuming is unchanged, find the sample size needed to halve the standard error of the sample mean.Show the mark scheme
Mark scheme
M1: (i) seen, divided by
A1: (i)
R1: (ii) its expected value is , which is not
R1: (ii) so it is a biased estimator that underestimates on average (the divisor corrects this)
M1: (iii) standard error is , so must double
A1: (iii)
Accept:Total for question 4: 12 marks
End of questions