C - What is Causation? Lesson

The What is Causation?

"Correlation does not imply causation" is a phrase used in science and statistics to emphasize that a correlation between two variables does not necessarily imply that one causes the other. In a widely studied example, numerous epidemiological studies showed that women who were taking combined hormone replacement therapy (HRT) also had a lower-than-average incidence of coronary heart disease (CHD), leading doctors to propose that HRT was protective against CHD. But controlled trials showed that HRT caused a small but statistically significant increase in risk of CHD. Re-analysis of the data from the epidemiological studies showed that women undertaking HRT were more likely to be from higher socio-economic groups, with better-than-average diet and exercise regimens. The use of HRT and decreased incidence of coronary heart disease were coincident effects of a common cause (i.e. the benefits associated with a higher socioeconomic status), rather than cause and effect, as had been supposed.

If the exposure, and only that exposure, was the immediate cause of the outcome, it would not be possible to have people in cell b. However, there are reasons why people can be in cell b, people who have been exposed and do not have the outcome, even when the exposure causes the outcome. One reason is that the exposure may not cause the outcome immediately. If you smoked a cigarette today, would you get lung cancer today? No, you will not. There is another reason why people can be in cell b. It can happen when the exposure is not necessarily enough, by itself, to produce the outcome, as, for example, when more than one exposure is needed to cause the outcome. As another example, the measles virus is the cause of measles, but not everyone who is exposed to the virus develops measles. Well, why not? Some people are immune because they have previously had measles or because they have been immunized with a measles vaccine.  

So, yes, it is possible for an exposure to produce an outcome and for cell b to still have people in it, that is, those who were exposed and who do not have the outcome. There are three basic reasons why.

    1. The exposure does not immediately cause the outcome.
    2. The exposure is not the only exposure needed to produce the outcome.
    3. Both reasons.

Now direct attention to cell c, where people who have not been exposed have the outcome, that is, where people who did not smoke and have developed lung cancer would be. How can you have people in cell c and still put a label on a cigarette pack that reads " ... smoking causes lung cancer ... "? The logical explanation is that there are other causes for the outcome of lung cancer. For example, radon and asbestos exposure can cause lung cancer.  

[CC BY 4.0] UNLESS OTHERWISE NOTED | IMAGES: LICENSED AND USED ACCORDING TO TERMS OF SUBSCRIPTION