The paired t ‐test

This chapter describes the difference between paired and unpaired data and it demonstrates that the paired t-test has greater power than the two-sample t-test when dealing with paired data. The paired t-test is used where data form natural pairs. Its classic use arises when we've observed the same individual under two different circumstances. The paired t-test offers the greatest advantage over the two-sample t-test when values are much higher in some individuals than in others, but all individuals show roughly the same change. It explains the source of its superior power and show how the paired t-test is performed. The chapter explores the merits of paired versus unpaired experimental designs. General statistical methods such as sample size estimation, determination of practical significance and one-sided testing can be applied to the paired t-test in the same manner that we have already seen for the two-sample t-test.