CHAPTER 7 Having Designs on Study Design 95

But you could not do causal inference unless you had a comparable comparison

group without liver cancer so that you could fill out your 2x2 table. Imagine that

you went back to the cancer center and were able to contact and enroll 30 patients

who had liver biopsies but were found not to have liver cancer to serve as controls.

Suppose that you interviewed this group and discovered that only two of them

reported high levels of alcohol intake. You could develop the 2x2 table like the one

shown in Figure 7-5.

As shown in Figure 7-5, what is important is not the 2x2 table itself, but the order

in which the counts are filled in. Notice that at the beginning of the study, you

already knew the case total was 30, and you had determined that your control total

would be 30 (although you are allowed to sample more controls if you want in a

case-control study).

The correct measure of relative risk to present for a case-control study is the OR (as

described in Chapter 14). It is important to acknowledge that when you present an

OR from a case-control study, you interpret it as an exposure OR, not an outcome

or disease OR. (It is also acceptable to present an OR in a cross-sectional study, but

in that case, you are presenting an outcome or disease OR.)

In a case-control study, because the condition is rare, you are sampling on the

outcome and calculating the likelihood that the cases compared to controls were

exposed. This study design is seen as extremely biased, which is why cohort stud-

ies are preferred, and are at a higher level of evidence. However, case-control

study designs are necessary for rare diseases.

Following a cohort over time

In the previous section, we pointed out that case-control studies are used for

rare diseases. Therefore, case-control studies do not have large sample sizes,

which is evident in Figure  7-5 where the total sample size is 60. In contrast,

cohort studies are used for studying common conditions, such as HTN, so they

FIGURE 7-5:

Example of

a typical

case-control

study 2x2 table.

© John Wiley & Sons, Inc.