qPaired Data: where observations come
in natural pairs.
q For
example:
q
A doctor might measure the effect of a drug by measuring
q
the physiological state of patients before and after applying
q
the drug. Each patient in this study has two observations, and
q
the observations are paired with each other. To determine the
q
drug’s effectiveness, the doctor looks at the difference
q
between the before and the after reading.
q
qPaired-data test is a one-sample
t-test
q To
test whether or not there is a significant difference, we use
q
one-sample t-test. It is because we are essentially looking at
q one
sample of data – the sample of paired difference.
q