An observational study (also called an epidemiological or population study) looks at large populations in an attempt to find trends. It is usually retrospective—that is, it examines what has happened in the past. Participants may fill out surveys or questionnaires on what they recall about particular behaviors, such as what foods they ate or what nutritional supplements they took in past years. Researchers don't change anything—they simply look at what is already going on. Such studies have most often tried to find connections between what people eat and the development of different diseases. A few have looked at the effect of taking nutritional supplements.
Observational studies are open to dispute and mixed interpretation by their very nature. For example, if an observational study finds that people who drink green tea develop less cancer, it is not necessarily the green tea that deserves the credit. Green tea drinkers may also tend to exercise more and to eat more healthful foods in general. Maybe it is those habits, and not the tea, that plays the most important role. Researchers try to look closely at the data and eliminate such factors, but it can never be done perfectly.