Investigating links between diet and health outcomes
This chapter discusses the methods used by nutritional scientists to investigate possible causal links between diet and disease or more broadly the effects of any dietary variations upon any health outcome. To reduce the risk of bias subjects, animal or human, are usually randomly allocated to control and experimental groups. Ideally, the person conducting the experiment should be unaware of which group any particular subject is in, especially when making outcome assessments. A weak correlation can be statistically significant without being of much value to a medical researcher trying to explain how, why and if two variables are really linked. Differences in some aspects of the environment, lifestyle or diet of several populations are related to their death rates or incidence of a particular disease or health-related characteristic. When large-scale cross-sectional surveys like the National Diet and Nutrition Survey are conducted, it is possible to look for links or correlations between the variables measured.