Introduction To Study Design

Introduction to Study Design

Research studies aim to establish a relationship between outcomes and exposure. Some exposures may be protective while others may pose risk. Does cigarette smoking cause cancer? Are nutritional supplements associated with increased health? Epidemiologists look at the patterns of disease in populations with the aim of controlling health problems.

There are a number of different study designs, arranged in the evidence hierarchy. The strength of the evidence increases as you move up the pyramid, though these are often harder to do, with the systematic review at the top.

• Systematic reviews (top of the pyramid)
• Randomized Controlled Trials (RCT)
• Cohort Studies
• Case-Control Studies
• Cross Sectional Studies
• Ecological Studies
• Case Reports and Case Series (bottom of the pyramid)

Types of Study Design

We can further classify the studies. Analytic studies are better able to examine causation as they have a control group. These are broken down into the experimental studies (in which we intervene and watch what happens) and the observation studies (in which we find people who are exposed and observe the difference). Descriptive studies look at a population and characterize the proportions of exposure and outcomes.

• Systematic Review (top of pyramid)
• Analytic Studies
  • Experimental Studies
    • Randomized Controlled Trials (RCT)
    • Pseudo-experimental studies
• Observational Studies
  • Cohort Studies
  • Case-Control Studies
• Descriptive Studies
  • Cross Sectional Studies
  • Ecologic Studies
  • Case Series and Case Reports
• Editorials and Expert Opinion (bottom of the pyramid)

The studies at the bottom of the pyramid (descriptive studies) do not look at causation (disease etiology). These simply describe the relationship between the exposure and the disease. These are useful to generate hypothesis, allocate resources and plan programs.

As we move up the pyramid, those types of studies provide more evidence for causation. These allow you to test the hypotheses generated in the descriptive studies as there is an explicit control group.