4 Measures of association
A measure of association compares the frequency of disease between exposed and unexposed people. This section defines the measures, derives their sampling distributions and confidence intervals, gives the tests of no association, and shows which measure each kind of case-control study estimates. Throughout, the \(2 \times 2\) table is laid out as in Section 1.2: \(a\) and \(b\) are the exposed and unexposed cases, \(c\) and \(d\) the exposed and unexposed non-cases, \(n_1 = a + c\), \(n_0 = b + d\), \(m_1 = a + b\), \(m_0 = c + d\).
4.1 Comparing two risks
4.2 Inference for the risk ratio and risk difference
4.3 Inference for the odds ratio
4.4 Testing for no association
4.5 Comparing rates
4.6 What a case-control odds ratio estimates
4.7 Problems
4.2 Inference for the risk ratio and risk difference
4.3 Inference for the odds ratio
4.4 Testing for no association
4.5 Comparing rates
4.6 What a case-control odds ratio estimates
4.7 Problems
Questions on this section
Stuck on something here? Ask below and it stays attached to this topic.