February 6, 20 A manufacturer of flashlights wants to know how well one of their newer styles is selling in a chain of large home- improvement stores. They select a simple random sample of 20 stores, record how many of the flashlights were sold in a 30-day period, and constructed a 95% confidence interval for the true mean number of flashlights sold. (a) Explain what would happen to the width of the confidence interval if the confidence level were increased to 98%. (b) How would we expect the width of the confidence interval to change if the flashlight manufacturer selected a much larger sample? Explain. (c) The 20 stores in the sample were actually the only stores who provided sales figures from 36 stores that were randomly chosen to be in the sample. Can the manufacturer adjust the confidence interval to take this nonresponse into account? If so, how? If not, why not?