Confidence intervals and p-values

This chapter begins with a discussion on confidence intervals for a single mean. It explains how to calculate the confidence interval for a single mean μ and then talks about its interpretation. The chapter extends the methodology to deal with μ 1 ‐ μ 2 . The role of the standard error is explained. A small standard error will produce a narrow confidence interval, giving us a very definite statement about the value of μ. With binary data, the chapter focuses on constructing confidence intervals for rates or proportions plus differences between those rates. The calculation of the confidence interval for any statistic, be it a single mean, the difference between two means, a median, a proportion, the difference between two proportions and so on, always has the same structure. The chapter explains the bootstrap confidence interval, and goes on to talk about hypothesis testing. It concludes with a discussion on p‐value calculation.