• Recognize observational studies and list the key components
• Describe confounding factors that may influence an association

Observational Studies

In an observational study, a researcher will observe an outcome without interfering. Instead of trying to assess cause and effect, an observational study is typically used when the goal is to learn about characteristics of a population or to compare groups within a population with respect to some characteristic. Sometimes observational studies are used because they might be the only way certain types of questions can be studied.

When designing an observational study, researchers are often looking for a relationship between two variables.

explanatory variable (factor of interest)

The explanatory variable is the independent variable that is of interest to the researcher.

The explanatory variable is what researchers change or select to see how it affects something else; it’s the “cause” or input that helps explain why an outcome happens. 

response variable (response factor)

The response variable is the dependent variable that allows the researcher to objectively compare the differences.

The response variable is what researchers measure to see if it changes based on the explanatory variable; it’s the outcome or result being studied. 

• Hours of sleep (explanatory variable) might explain test scores (response variable)
• Amount of rainfall (explanatory variable) might explain crop yields (response variable)

In observational studies, researchers can only observe and measure what naturally occurs; they cannot assign participants to different groups, control the conditions, or isolate specific variables like they would in an experiment. Due to a lack of control, observational studies may inherently be at risk of containing confounding biases, which are outside of the control of the researcher. 

confounding variable

A confounding variable is a variable that was not accounted for in a study and may actually influence other variables in the study.

An observational study can show an association between variables, but it cannot establish a cause-and-effect relationship since the researchers are not controlling the study. Remember that the researcher is an observer, not an influencer.