1) If we are very certain that the true standard deviation of the number of defects per screen is below 2, what sample size would be required so that the width of the 95% confidence interval for the mean number of defects per screen is at most 0.39? n=20 s=1.423
2) A web based software company is interested in estimating the proportion of individuals who use the Firefox browser. In a sample of 200 of individuals, 38 users stated that they used Firefox. Using this data, construct a 99% confidence interval for the proportion of all individuals that use Firefox. What sample size would be required so that the width of the 99% confidence interval would be at most 0.03 units wide? Be as conservative as possible with your answer!