Use all data on cell phones Refer to the exercise 1. When we use the data for all 32 subjects, MINITAB reports results in the following for the Wilcoxon signed-ranks test. Wilcoxon signed-ranks test results Test of median = 0.000000 versus median not = 0.000000 I N for Test | Wilcoxon Statistic P Estimated Median diff | 32 32 490.0 0.000 47.25 a. State the null and alternative hypotheses for this test. b. Explain how MINITAB found the value reported for the Wilcoxon test statistic. c. Report and interpret the P-value. d. Report and interpret the estimated median. Exercise 1 More on cell phones Refer to Exercise 2. That analysis did not take into account the magnitudes of the differences in reaction times. Show how to do this with the Wilcoxon signed- ranks test, illustrating by using only the four observations shown in the table there. a. State the hypotheses for the relevant one-sided test. b. Create the sampling distribution of the sum of ranks for the positive differences. C. Find the P-value, and interpret. Exercise 2 Cell phones and reaction times Example 12 in Chapter compared reaction times in a simulated driving test for the same students when they were using a cell phone and when they were not The table shows data for the first four students. For all 32 students, 28 had faster reaction times when not using the cell phone and 8 had faster reaction times when using it. a. Are the observations for the two treatments independent samples, or dependent samples? Explain. b. Let p denote the population proportion who would have a faster reaction time when not using a cell phone. Estimate p based on this experiment. c. Using all 32 observations, find the test statistic and the P-value for the sign test of HO: p = 1/2 against Ha: p > 1/2. Interpret. d. What is the parametric method for comparing the scores? What is an advantage of it over the sign test? (Hint: Does the sign test use the magnitude of the difference between the two scores, or just its direction?) Reaction times in cell phone study Using Cell Phone? Student Difference No Yes 1 604 636 32 2 556 623 67 3 540 615 75 522 672 150\fComparing more bumpers Refer to the exercise 1. a. Would the results of your analysis change if for the second Bumper A the repair cost was $9000 instead of $2500? What does this illustrate about the analysis? b. Suppose the company actually wanted to compare three bumper types. Which significance test could they use to do this if they did not want to assume that the repair costs have a normal distribution for each bumper type? Exercise 1 Car bumper damage An automobile company compares two types of front bumper for their new model by driving sample cars into a concrete wall at 15 miles per hour. The response is the amount of damage to the car, as measured by the repair costs, in dollars. Due to the costs, the study uses only six cars, obtaining results for three bumpers of each type. The results are in the table a. Find the ranks and the mean rank for each bumper type. b. Show that there are 20 possible allocations of ranks to the two bumper types. c. Explain why the observed ranks for the two groups are one of the two most extreme ways the two groups can differ, for the 20 possible allocations of the ranks. d. Explain why the P-value for the two-sided test equals 0.10. Bumper A | Bumper B 2100 1100 2500 1300 2300 1400Telephone holding times In Exercise 1, the telephone holding times for Muzak and classical music were Muzak 0, 1. 4, 6, 3 Classical 13, 9. 8, 15. 7 a. For comparing these two groups with the Wilcoxon test, report the ranks and the mean rank for each group. b. Two groups of size 5 each have 252 possible allocations of rankings. For a two-sided test of HO: identical distributions with these data, explain why the P-value is 2/252 = 0.008. Interpret the P-value. Exercise 1 How long do you tolerate being put on hold? Examples 1-4 and 7 in Chapter 14 referred to the following randomized experiment: An airline analyzed whether telephone callers to their reservations office would remain on hold longer, on average, if they heard (3) an advertisement about the airline, (b) Muzak, or (c) classical music. For 15 callers randomly assigned to these three conditions, the table shows the data. It also shows the ranks for the 15 observations, as well as the mean rank for each group and some results from using MINITAB to conduct the Kruskal-Wallis test a. State the null and alternative hypotheses for the Kruskal Wallis test. b. Identify the value of the test statistic for the Kruskal-Wallis test, and state its approximate sampling distribution, presuming HO is true. c. Report and interpret the P-value shown for the Kruskal-Wallis test. d. To find out which pairs of groups significantly differ, how could you follow up the Kruskal-Wallis lest? Telephone holding times by type of recorded message Recorded Message | Holding Time Observations | Ranks Mean Rank Muzak 0, 1. 3, 4, 6 1, 2, 5, 5, 6, 8 4.5 Advertisement 1, 2, 5, 8, 11 2.5, 4, 7, 10.5, 13 7.4 Classical 7, 8. 9, 13, 15 9, 10.5. 12, 14, 15 12.1 Kruskal-Wallis Test: Holding Time Versus Group Group N Median |Ave Rank Muzak 5 3.000 4.5 Advert 5 5. 000 7.4 Classical | 5 9.000 12.1 H = 7.38 DF = 2 P = 0.025 (adjusted for ties)Teenage anorexia Example 8 in Section 9.3 and Exercise 1 described a study that used therapy to treat teenage girls who suffered from anorexia. The girls were randomly assigned to the cognitive behavioral treatment (Group 1) or to the control group (Group 2). The study observed the weight change after a period of time. The output shows results of a nonparametric comparison. a. Interpret the reported point estimate of the difference between the population medians for the weight changes for the two groups. b. Interpret the reported confidence interval, and summarize the assumptions on which it based c. Report a P-value for testing the null hypothesis of identical population distributions of weight change. Specify the alternative hypothesis, and interpret the P-value. MINITAB output comparing weight changes N Median Cognitive_change | 20 1.400 Control_change 26 -0.350 Point estimate for ETA1-ETA2 is 3.0595.0 Percent CI for ETA1-ETA2 is (-0.80, 8.10)W = 807.0Te Exercise 1 Teenage anorexia Example 8 in Section 9.3 described a study that used a cognitive behavioral therapy to treat a sample of teenage girls who suffered from anorexia. The study observed the mean weight change after a period of treatment. Studies of that type also usually have a control group that receives no treatment or a standard treatment. Then researchers can analyze how the change in weight compares for the treatment group to the control group. In fact, the anorexia study had a control group that received a standard treatment. Teenage girls in the study were randomly assigned to the cognitive behavioral treatment (Group 1) or lo the control group (Group 2). The figure shows box plots of the weight changes for the two groups (displayed vertically). The output shows how MINITAB reports inferential comparisons of those two means. MINITAB Output Comparing Mean Weight Changes group N Mean StDev | SE Mean cog_behav 29 3.01 7.31 1.4 control 6-0.45 7.99 1.8 Difference = mu (cog_behav) - mu (control) Estimate for difference: 3.4569095%% CI for difference 25 15 : 10 cog behay control group Box plots of weight change for anorexia study. a. Report and interpret the P-value for testing HO: p1 = p2 against Ha: p1, # p2. b. Summarize the assumptions needed for the analysis in part a. Based on the box plots, would you be nervous if you had to perform a one-sided test instead? Why? c. The reported 95% confidence interval tells us that if the population mean weight change is less for the cognitive behavioral group than for the control group, it is just barely less (less than 1 pound), but if the population mean change is greater, it could be nearly 8 pounds greater. Explain how to get this interpretation from the interval reported