Testing for zero correlation

Testing for zero correlation Test

Spec 5.2 · Edexcel International A Level Further Maths: Subtopic test

Studying this course? Keep your progress in one place.

Two ways to do this test

Question by question

One question at a time. Each answer is marked the moment you hand it in, so you learn as you go. Drago helps if you get stuck. All 10 questions, or just 5.

Exam mode

The whole paper in one go, timed like the real exam. Nothing is marked until you hand it in, then you get every mark explained.

10 questions, 27 marks

Edexcel International A Level Further Maths

Testing for zero correlation

Total 27 marks

Name

Class

Date

  1. 1
    A teacher records the hours of revision and the test score of each of 10 randomly chosen students. The data may be assumed to come from a bivariate Normal distribution. The product moment correlation coefficient for the sample is r=0.62r=0.62. The teacher tests at the 5% significance level whether there is any correlation between revision hours and score. For n=10n=10 the two-tailed 5% critical value is 0.6319.
    (a)
    Which pair of hypotheses should the teacher use, where ρ\rho is the population product moment correlation coefficient?
    [1 mark]
    • AH0H_0: ρ=0\rho=0, H1H_1: ρ>0\rho>0
    • BH0H_0: ρ=0\rho=0, H1H_1: ρ≠0\rho\neq0
    • CH0H_0: r=0r=0, H1H_1: r≠0r\neq0
    • DH0H_0: ρ≠0\rho\neq0, H1H_1: ρ=0\rho=0
    Show the mark scheme

    Mark scheme

    Answer: B
    (b)
    Which conclusion is correct?
    [1 mark]
    • AReject H0H_0, because 0.620.62 is greater than 0.050.05
    • BReject H0H_0: there is evidence of correlation between revision hours and score
    • CThere is insufficient evidence to reject H0H_0, because 0.62<0.63190.62<0.6319: no evidence of correlation
    • DH0H_0 is true, so revision hours and score are not related
    Show the mark scheme

    Mark scheme

    Answer: C
    (c)
    Suppose instead that the relationship between revision hours and score were known to be increasing but clearly curved. Name a more suitable measure of correlation and give a reason.
    [2 marks]
    Show the mark scheme

    Mark scheme

    B1: Spearman's rank correlation coefficient
    B1: it measures monotonic association, whereas the product moment correlation coefficient test needs a linear relationship and bivariate Normal data

    Accept: 'it does not need the data to be bivariate Normal'

    Total for question 1: 4 marks

  2. 2
    A tutor believes that students who complete more practice papers achieve higher mock exam ranks. For a random sample of 8 students, the number of practice papers and the mock mark are each ranked with rank 1 for the highest, and ∑d2=26\sum d^2=26. For n=8n=8 the 5% critical value for Spearman's coefficient is 0.6429 for a one-tailed test and 0.7381 for a two-tailed test.
    (a)
    Which alternative hypothesis should the tutor use, where ρs\rho_s is the population rank correlation coefficient?
    [1 mark]
    • AH1H_1: ρs>0\rho_s>0
    • BH1H_1: ρs≠0\rho_s\neq0
    • CH1H_1: ρs<0\rho_s<0
    • DH1H_1: rs>0r_s>0
    Show the mark scheme

    Mark scheme

    Answer: A
    (b)
    Calculate the sample value of Spearman's rank correlation coefficient.
    [1 mark]
    • A0.3100.310
    • B0.7000.700
    • C−0.690-0.690
    • D0.6900.690
    Show the mark scheme

    Mark scheme

    Answer: D
    (c)
    Carry out the test at the 5% significance level and state the conclusion in context.
    [2 marks]
    Show the mark scheme

    Mark scheme

    B1: 0.690>0.64290.690>0.6429, so reject H0H_0
    B1: there is sufficient evidence of positive correlation between the number of practice papers completed and the mock exam rank

    Accept: follow-through from their
    rsr_s in (b)

    Total for question 2: 4 marks

  3. 3
    A cafe owner believes that daily sales of hot drinks fall as the outside temperature rises. Over 12 randomly chosen days the owner records the temperature and the number of hot drinks sold. The data may be assumed to come from a bivariate Normal distribution, and the sample product moment correlation coefficient is r=−0.632r=-0.632. For n=12n=12 the one-tailed critical values for the product moment correlation coefficient are 0.4973 at the 5% level and 0.6581 at the 1% level.
    (a)
    State the hypotheses for the owner's test and the critical region at the 5% level.
    [3 marks]
    Show the mark scheme

    Mark scheme

    B1: H0H_0: ρ=0\rho=0
    B1:
    H1H_1: ρ<0\rho<0 (one-tailed, because the owner expects sales to fall as temperature rises)
    B1: critical region
    r≤−0.4973r\le-0.4973
    Accept:
    r<−0.4973r<-0.4973
    Do not accept:
    r≥0.4973r\ge0.4973
    (b)
    Carry out the test at the 5% level, stating your conclusion in context, and say what the result would be at the 1% level.
    [4 marks]
    Show the mark scheme

    Mark scheme

    M1: compares r=−0.632r=-0.632 with −0.4973-0.4973, so −0.632<−0.4973-0.632<-0.4973
    A1: reject
    H0H_0
    B1: there is evidence that hot drink sales are negatively correlated with temperature, so sales fall as temperature rises

    B1: at the 1% level
    −0.632>−0.6581-0.632>-0.6581, so H0H_0 is not rejected and there is insufficient evidence of negative correlation at that level
    Accept:
    ∣r∣=0.632<0.6581|r|=0.632<0.6581

    Total for question 3: 7 marks

  4. 4
    A school investigates whether weekly screen time and average nightly sleep are correlated. For ten randomly chosen students A to J, the weekly screen times in hours are 12, 25, 8, 30, 18, 5, 22, 15, 28 and 10, and the average nightly sleep in hours is 8.0, 6.5, 8.5, 6.0, 7.2, 8.8, 7.5, 6.9, 6.6 and 7.8 respectively. For n=10n=10 the two-tailed 5% critical value for Spearman's coefficient is 0.6485.
    (a)
    Test at the 5% significance level whether there is correlation between screen time and sleep, using Spearman's rank correlation coefficient. State your conclusion in context.
    [6 marks]
    Show the mark scheme

    Mark scheme

    B1: H0H_0: ρs=0\rho_s=0; H1H_1: ρs≠0\rho_s\neq0
    M1: both sets ranked in the same direction, e.g. screen time for A to J: 4, 8, 2, 10, 6, 1, 7, 5, 9, 3 and sleep: 8, 2, 9, 1, 5, 10, 6, 4, 3, 7

    A1:
    ∑d2=318\sum d^2=318
    A1:
    rs=1−6×31810×99=−0.927r_s=1-\frac{6\times318}{10\times99}=-0.927
    Accept:
    +0.927+0.927 if one set is ranked in the opposite direction, with the sign explained
    B1:
    ∣−0.927∣>0.6485|-0.927|>0.6485
    A1: reject
    H0H_0: there is evidence of correlation, and the negative sign shows students with more screen time tend to sleep less
    (b)
    A second school tests ten students in the same way and finds rs=−0.55r_s=-0.55. Carry out the two-tailed test at the 5% level for this school and comment on the two results.
    [6 marks]
    Show the mark scheme

    Mark scheme

    M1: compares ∣−0.55∣|-0.55| with 0.64850.6485, so 0.55<0.64850.55<0.6485
    A1: insufficient evidence to reject
    H0H_0
    B1: no evidence at the 5% level of a correlation between screen time and sleep at the second school

    B1: this does not prove there is no correlation, because with only ten students the test may fail to detect a real correlation

    B1: the two samples give different conclusions because of sampling variation, and the first school's result was much stronger

    B1: neither result shows that screen time causes less sleep, because correlation does not imply causation

    Total for question 4: 12 marks

End of questions

Subtopic tests