General Instructions: For all confidence intervals (confidence bounds) you compute in these problems, draw a sketch of the confidence interval (confidence bound) on the appropriate scale.
Warning: Make sure you know what population parameter you are finding a confidence interval for. If the question asks about a mean, you are interested in \(\mu\). If the question asks about a count, proportion, or percentage calculated from \(n\) trials, you are interested in \(p\).
Note 1: For confidence intervals (confidence bounds) for a population mean, do not use the 'large sample confidence interval' given by equation 8.8 on page 386. Use the \(t\)-distribution-based confidence interval (confidence bound).
Note 2: For confidence intervals (confidence bound) for a population proportion, compute the confidence interval (confidence bound) using binom.agresti.coull from the R package binom as we did in class. You do not have to do this by hand. Use R.
Choose 2 problems from Quizzes 7—11 which you were most uncertain about at the time of the quiz or now, and write up solutions to those problems. Ideally, you should do this without looking at your previous solutions or the solutions on eCampus, as practice for Exam 2.
Given your understanding of the lectures, performance on the quizzes, homeworks, and Exam 1, study habits, and any other relevant circumstances, what percentage score do you expect to earn on Exam 2? Why? State your prediction, and write 3 to 4 sentences justifying your prediction.
As an incentive to give this some real thought and predict as accurately as possible, if your prediction is within \(\pm\) 5 percentage points of your Exam 2 percentage score, you will earn an additional 3 percentage points on your percentage score for Exam 2.