All flashcards topics

Hypothesis tests for the difference between two meansEdexcel International A Level Further Maths: Flashcards

What these 14 flashcards ask

  • Hypotheses for testing whether two means are equal?
  • Distribution of \bar X-\bar Y for independent Normal samples?
  • Do the variances of \bar X and \bar Y add or subtract?
  • Test statistic for two means with variances known?
  • Standard error of \bar X-\bar Y?
  • What if the variances are unknown and both samples are large?
  • What justifies the Normal approximation for large samples?
  • One-tailed 5\% critical value for z?
  • Two-tailed 5\% critical values?
  • One-tailed 1\% critical value?
  • Why must the samples be independent?
  • A test shows \muA<\muB. Does it show every A value is smaller?
  • How do you word a conclusion when H0 is not rejected?
  • Which order of subtraction fits H1:\muA<\muB?

Exam questions on Hypothesis tests for the difference between two means

  1. Two machines, XX and YY, fill bags with sugar. The masses, in grams, are Normally distributed, with known standard deviations of 44 for machine XX and 55 for machine YY. A random sample of 2020 bags from XX has a mean mass of 502.1502.1 and a random sample of 2525 bags from YY has a mean mass of 499.8499.8. A test of H0:μX=μYH_0:\mu_X=\mu_Y against H1:μX≠μYH_1:\mu_X\neq\mu_Y is carried out at the 5%5\% significance level.
    Complete the test and state your conclusion in context.2 marks
  2. Seedlings are grown using either fertiliser AA or fertiliser BB. The heights are Normally distributed, with known standard deviations of 2.12.1 cm for AA and 2.42.4 cm for BB. A random sample of 3030 seedlings grown with AA has a mean height of 14.614.6 cm and a random sample of 4040 seedlings grown with BB has a mean height of 13.813.8 cm. A gardener wants to test, at the 5%5\% significance level, whether fertiliser AA gives a greater mean height than fertiliser BB.
    Carry out the test and state your conclusion in context.2 marks
  3. A supermarket chain compares customer spending at two stores, PP and QQ. A random sample of 6060 customers at PP spent a mean of £42.50 with sample variance 8181, and a random sample of 5050 customers at QQ spent a mean of £39.80 with sample variance 6464. The distributions of spending are not assumed to be Normal. The chain tests H0:μP=μQH_0:\mu_P=\mu_Q against H1:μP≠μQH_1:\mu_P\neq\mu_Q at the 5%5\% significance level.
    State the approximate distribution of XˉP−XˉQ\bar X_P-\bar X_Q under H0H_0, and justify why this distribution may be used.3 marks
See the full worksheet

Written by the Exaim team, led by Shaun Daswani (Head of Upper Secondary, Improve ME Institute; MSc Financial Mathematics, Imperial College London; BSc, UCL) and Jason Daswani (operational lead, Improve ME Institute; LSE).