814 APPENDIX D z = -5.98, critical values are {1.96, P@value = 0.000. Randomization test with 1000 resamplings yields no results at least as extreme as d = -0.85072°F. Bootstrap 95% confidence interval: -1.04°F 6 md 6 -0.66°F (which can vary). All of the results suggest rejection of H0: md = 0°F. There appears to be a significant difference between the 8 AM and 12 AM second-day temperatures. It appears that there is generally a significant difference between body temperatures measured at 8 AM and at 12 AM. 3. r = 0.206 and critical values are {0.237 which suggests no correlation. rs = 0.252 and critical values are {0.238 which suggests that there is a correlation. These results conflict, but a scatterplot shows no clear pattern, so conclude that there is not a correlation. 5. Using 98.20°F we get P99 = 99.64°F. Using 98.6°F we get P99 = 100.04°F. The difference is 0.40°F, which is not insignificant, but it probably does not make too much of a difference in practice. 7. Test statistic from parametric t test (Section 8-2): t = -7.102, critical values are t = {1.986 (Table: {1.987), P@value = 0.000 and 95% confidence interval is 97.99°F 6 m 6 98.26°F. Nonparametric sign test: Test statistic is z = -4.91, critical values are {1.96, P@value = 0.000. Nonparametric Wilcoxon signed-ranks test: Test statistic is z = -5.77, critical values are {1.96, P@value = 0.000. Results can vary, but a randomization test with 1000 resamplings yields no results at least as extreme as 98.12366°F. Bootstrap 95% confidence interval: 97.99°F 6 md 6 97.25°F (which can vary). All of the results suggest rejection of H0: m = 98.6°F. It appears that the mean body temperature at 12 AM is different from 98.6°F. 9. Typical results are shown in this chapter in the discussion of simulations. It would be very rare to get a simulated sample with a mean as extreme as 98.2°F, and this shows that the assumption of a mean equal to 98.6°F is probably an incorrect assumption. It appears that the mean body temperature is not 98.6°F. 8. There is a pattern of an upward trend, so the process is out of statistical control. 9. x = 7.3, median = 6.5, s = 4.2. These statistics do not convey information about the changing pattern of the data over time. 10. H0: m1 = m2. H1: m1 7 m2. Test statistic: t = 2.879. P@value = 0.0026 (Table: 60.005). Critical value: t = 2.376 (Table: 2.426). Reject H0. There is sufficient evidence to support the claim that the mean number of details recalled is lower for the stress group. It appears that “stress decreases the amount recalled,” but we should not conclude that stress is the cause of the decrease. Chapter 15 Answers Holistic Exercises 1. Test statistic from parametric t test (Section 9-3): t = -8.484, critical values are t = {1.996 (Table: {2.000), P@value = 0.000 and 95% confidence interval is -1.05°F 6 md 6 -0.65°F. Nonparametric sign test: Test statistic is z = -5.86, critical values are {1.96, P@value = 0.000. Nonparametric Wilcoxon signed-ranks test: Test statistic is
RkJQdWJsaXNoZXIy NjM5ODQ=