ENGI 4421 Probability and Statistics

Faculty of Engineering and Applied Science


Hypothesis Test Tutorial Example — Solution


  1. State the appropriate null and alternative hypotheses.


    The burden of proof is on demonstrating that the mean breaking load of the new wires is more than 5 N greater than that of the existing wires, that is, greater than 105.0 N.   This is a one-sided alternative (upper tailed test).   Therefore

    Ho : mu = 105  vs.  Ha : mu > 105

    [Note that, as the complement of the alternative hypothesis, the null hypothesis also includes   µ < 105.0.]


  2. Conduct the appropriate hypothesis test.


    Note that while the breaking load for wires produced by the existing process is normally distributed, the question gives no such guarantee for the distribution of the breaking load of wires produced by the new process.

    The sample size is greater than 30.
    The central limit theorem therefore ensures that the distribution of the sample mean is normal, to at least a good approximation.   Furthermore, the t distribution with 35 degrees of freedom may be replaced by the standard normal (z) distribution, provided that distances from means are rounded off to no more than two significant figures.

    Method 1: [graph showing upper-tailed rejection region]

    c = mu + z_.05 s/sqrt(n) = 105.8
    or, using the more precise t distribution with 35 degrees of freedom,
    c = mu + t_.05,35 s/sqrt(n) = 105.8
    sample mean 106.0 > c = 105.8  therefore reject Ho

    Method 2:

    t_obs = 2
    t_.05, 35 = 1.69  or  z_.05 = 1.64
    t_obs > t_c  therefore reject Ho

    Method 3:

    t_obs = 2
    Using the t Calculator spreadsheet,
    P[T > t_obs] = .026654 < alpha
    or, using the table of the c.d.f. of the standard normal distribution,
    P[Z > t_obs] approx= .02275 < alpha
    By any of these three methods, we reject the null hypothesis in favour of the alternative hypothesis at a level of significance of 5%.


  3. Should you advise the client to invest in the new process?


    We have sufficient evidence to reject the null hypothesis in favour of the alternative hypothesis.   Therefore

      YES  


  4. What would the decision be if the sample mean had been 104 N?


    We are seeking evidence for   µ > 105.
    xBar < 105 which is clearly inconsistent with   µ > 105.
    The rejection region is to the right of   x = 105, but this sample mean is to the left of   x = 105.   No hypothesis test is needed here.   We would decide immediately to retain the null hypothesis and the advice would be to

      not invest in the new process  


          BONUS QUESTION:

  1. If the true mean breaking load of the new wires is 106.0 N, then what is the probability that another random sample of 36 wires, with the same sample standard deviation, will lead to an incorrect decision?


    [graphs of pdf for means of 105 and 106] We need Method 1 from part (b) above.
    The rejection region, calculated on the basis that   µ = 105, has its boundary at   c = 105.8448 [we need greater precision here].
    [If z is used instead of t35, then c = 105.8224]
    If   µ = 106 then the null hypothesis is false.
    The incorrect decision is to retain the null hypothesis, which will happen iff the sample mean does not fall in the rejection region.   Using the more precise t distribution,
    P[Xbar < c | mu = 106] = .38
    Approximating by the standard normal distribution, (which allows the tables of the standard normal c.d.f. to be used),
    P[Xbar < c | mu = 106] = .36
    Therefore the probability of an incorrect decision in this case is

    beta(106) = 38%


  2. What type of error is the event in part (e)?


    If the population mean is 106 N, then the alternative hypothesis is true and the null hypothesis is false.
    Not rejecting the null hypothesis when it is false is a

      type II error  


          An Excel spreadsheet for this example is available here.
      Return to the index of solutions   [Index of solutions]
      Return to your previous page   [Return to your previous page]
          Created 2007 11 08 and most recently modified 2018 01 30 by Dr. G.H. George