Objectives for this activity
During this activity, you will:
- Identify an observational study.
- Distinguish between experimental and observational studies.
- Identify possible confounding factors that might explain an apparent association.
In section [2C], you learned about experimental studies, and in the preview assignment for this activity, you learned that observational studies are sometimes used when an experiment would be untenable or unethical to conduct. This Forming Connections activity should help you synthesize the ideas about experiments and observational studies that you seen so far. In particular, you’ll see that observational studies are different from experimental studies because confounding factors can create associations in observational studies in ways that shouldn’t occur in controlled experiments with random assignment. In this activity, you’ll use real world data to investigate what it means to conduct an observational study.
Effective Vaccines?
In the previous in-class activity, you learned about a type of statistical study known as an experimental study. However, it is not always appropriate to use experimental studies.
Work in pairs to discuss Question 1. As you do, you may wish to reflect on the example in the preview assignment in which the researcher wanted to explore how smoking habits relate to depression.
Guidance
[Intro: In certain situations, it is not appropriate to use an experiment to research a question. For example, in the preview assignment for this activity, you saw an example in which a researcher wanted to explore how smoking habits relate to depression. Why couldn’t, or shouldn’t, that research be conducted via experimental design? You can probably come up with one or two good reasons. Therefore, observational studies are sometimes necessary to research a question if ethical issues would prevent an experimental design.]
Question 1
Can you think of a situation in which collecting data to answer a question is more appropriate because an experiment would not be appropriate?
Let’s explore a recent, important example of an observational study.
In March 2020, COVID-19 was declared a pandemic by the World Health Organization. In December 2020, vaccines using Messenger RNA technology were given emergency use authorization by the Food and Drug Administration in the United States. Over the next 13 weeks, 3,950 health care personnel, first responders, and other essential and frontline workers who had received the vaccine completed weekly COVID-19 testing to determine whether they had tested positive for COVID-19. In this study, researchers were following the effectiveness of the vaccines in a real-world setting.
For more information about this study, visit https://www.cdc.gov/mmwr/volumes/70/wr/mm7013e3.htm.
Work in groups or pairs to answer Questions 2 – 6.
question 3
Identify at least one potentially confounding variable in this study.
question 4
What are some differences between an experimental study and an observational study?
You may wish to make some notes for yourself if you haven’t already about the key differences between experiments and observational studies.
As you answer Questions 5 and 6, recall the definition of a confounding variable: Remember the definition of a confounding variable: a variable that was not accounted for in a study and may actually influence other variables in a study.
question 5
A PhD student collects data at a local elementary school. For each student, she records their age, grade, height, weight, shoe size, GPA, and score on a state-wide reading test for elementary school-aged children.
Part A: Is this an experimental or observational study?
Part B: The PhD student observes that students with larger shoe sizes tend to score higher on the state-wide reading test. She concludes that having bigger feet improves reading ability. Can you explain why her reasoning is likely to be incorrect? Can you think of another explanation for the higher test scores?
question 6
A study finds that people living in high-density urban areas develop fatal lung cancer at lower rates than people living in low-density rural areas.
Part A: Is this an experimental or observational study?
Part B: A student reads this study and determines that living near many people prevents cancer. Can you think of other things that might explain why low-density areas see higher rates of lung cancer?
Guidance
[Wrap-up: You’ve seen that experimental studies have treatments, random assignment of participants, cause-and-effect relationships, and controls. Observation studies on the other hand do not have different treatments, they do not randomly assign participants to treatments, and they have a lack of control (or knowledge) of confounding variables. You may wish to keep a list of these differences handy until you develop a deep understanding of the difference between experiments and observational studies. ]
