You may work together with other students on Part A, but I would like each of you to work independently on Part B and submit the complete assignment individually.
Part A.
Several different calculations of P-value have been proposed for two-sided tests of a binomial proportion: normal approximation, normal approximation with continuity correction, exact binomial P, and exact binomial mid-P. Each definition defines a corresponding confidence interval. For each definition, draw a graph plotting actual coverage against the true value of the binomial proportion, for sample sizes 10, 100 and 1000.
Part B.
The numbered problems are from Agresti, A. (1996), An Introduction to Categorical Data Analysis, Wiley.
Chapter 1:
1.12, 1.15
Problem 1.15 gives yet another way to calculate confidence intervals. For this method, plot a coverage graph like the ones in Part A.
Chapter 2:
2.1, 2.4, 2.5, 2.10, 2.11, 2.12, 2.18