Date | May 2010 | Marks available | 5 | Reference code | 10M.2.hl.TZ0.4 |
Level | HL only | Paper | 2 | Time zone | TZ0 |
Command term | Show that | Question number | 4 | Adapted from | N/A |
Question
The weights, X grams, of tomatoes may be assumed to be normally distributed with mean μ grams and standard deviation σ grams. Barry weighs 21 tomatoes selected at random and calculates the following statistics.∑x=1071\);\(∑x2=54705
(i) Determine unbiased estimates of μ and σ2 .
(ii) Determine a 95% confidence interval for μ .
The random variable Y has variance σ2 , where σ2>0 . A random sample of n observations of Y is taken and S2n−1 denotes the unbiased estimator for σ2 .
By considering the expression
Var(Sn−1)=E(S2n−1)−{E(Sn−1)}2 ,
show that Sn−1 is not an unbiased estimator for σ .
Markscheme
(i) ¯x=107121=51 A1
S2n−1=5470520−1071220×21=4.2 M1A1
(ii) degrees of freedom =20 ; t-value =2.086 (A1)(A1)
95% confidence limits are
51±2.086√4.221 (M1)(A1)
leading to [50.1,51.9] A1
[8 marks]
Var(Sn−1)>0 A1
E(S2n−1)=σ2 (A1)
substituting in the given equation,
σ2−E(Sn−1)>0 M1
it follows that
E(Sn−1)<σ A1
this shows that Sn−1 is not an unbiased estimator for σ since that would require = instead of < R1
[5 marks]
Examiners report
Most candidates attempted (a) although some used the normal distribution instead of the t-distribution.
Many candidates were unable even to start (b) and many of those who did filled several pages of algebra with factors such as n / (n−1) prominent. Few candidates realised that the solution required only a few lines.