OBSERVATIONAL DATA
Today homeopathy is back with a vengeance. Why? Nobody really knows. The reasons are probably complex.3. One contributing factor seems to be that observational studies regularly show that patients receiving homeopathic treatments experience benefit.4,5. Others insist that any treatment that has been around for 200 years has “stood the test of time.”
Experience, the “test of time,” and observational studies all have one thing in common: the lack of a control. To be able to draw conclusions about cause and effect, a positive or negative control is needed. Observational data are, by definition, uncontrolled and unreliable. Causal inferences are therefore not appropriate.
Of course, medicine has a long tradition of disregarding this rather obvious fact.6. Whenever doctors administer a treatment to a patient outside of a clinical trial (that is, in an uncontrolled fashion), they are likely to attribute the ensuing outcome to the specific effects of their intervention. In other words, practitioners regularly make causal inferences on less than solid grounds.
It would be constructive to create conceptual clarity about what really is going on in such a situation. Figure 1 schematically depicts the case of a patient (or a group of patients) receiving homeopathy. Over time, symptoms improve, and a therapeutic effect is therefore perceived. The assumption of homeopaths is, therefore, that this “perceived therapeutic effect” is attributable to the specific effects of their intervention.